© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 7178
    Prev
    Next
    INDEX
    Explanations

    hygiene syndrome instructions

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

    technical and medical terms within scientific or clinical contexts.

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

    The neuron fires on specialized scientific or technical method and measurement terms (e.g. “logic gate operations,” “duplex regions,” “readout,” “visual fields,” “metabolic syndrome,” etc.).

    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
     will
    -1.83
     when
    -1.66
     that
    -1.55
     then
    -1.53
     because
    -1.48
     intest
    -1.46
     from
    -1.35
     now
    -1.29
     this
    -1.28
     these
    -1.27
    POSITIVE LOGITS
     atractiva
    1.56
     vejo
    1.46
    without
    1.42
     reconocida
    1.41
     primeras
    1.38
     teria
    1.37
     très
    1.37
     อ
    1.34
    DOES
    1.34
    bable
    1.34
    Activations Density 0.151%

    No Known Activations