© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 39084
    Prev
    Next
    INDEX
    Explanations

    medical conditions and diseases

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

    references or citations in academic papers, particularly those in parentheses or brackets.

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

    The neuron is triggered by numeric expressions (digits, decimals, percentages, citation numbers) in the text.

    oai_token-act-pair · o4-miniTriggered 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
     of
    -1.89
     Each
    -1.52
    Opinión
    -1.51
    六十
    -1.41
     (
    -1.41
     Some
    -1.38
    Kesimpulan
    -1.38
    Цели
    -1.35
     each
    -1.33
    SEGUIR
    -1.33
    POSITIVE LOGITS
    1.76
    oved
    1.56
    \&
    1.54
    erunner
    1.49
     its
    1.48
     .........
    1.46
    itself
    1.46
    doesn
    1.44
     but
    1.43
    "...
    1.41
    Activations Density 0.057%
    No Known Activations