© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 20202
    Prev
    Next
    INDEX
    Explanations

    cerebrospinal fluid

    np_acts-logits-general · gemini-2.5-flash-lite

    terminology related to cerebrospinal fluid and neurological conditions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron consistently fires on references to cerebrospinal fluid (CSF) and related clinical/diagnostic terms.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to cerebrospinal fluid and meningeal/CNS contexts, especially CSF-related conditions, diagnostics, or pathology.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    medical terms related to cerebrospinal fluid (CSF) and neurological conditions.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    盉
    -1.48
     trusty
    -1.41
     compromisos
    -1.39
    くちゃ
    -1.35
     δὲ
    -1.35
     was
    -1.30
     imó
    -1.27
    elesen
    -1.27
     combustível
    -1.26
     famílias
    -1.24
    POSITIVE LOGITS
    .
    1.44
    wała
    1.25
    тием
    1.24
     ۱۴۰۰
    1.15
    栎
    1.13
    fx
    1.13
    '),
    1.13
     ";
    1.12
    amkeit
    1.12
    dru
    1.11
    Activations Density 0.221%

    No Known Activations