© 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. 22-GEMMASCOPE-RES-131K
    7. 130214
    Prev
    Next
    INDEX
    Explanations

    The neuron activates strongly whenever it encounters the substring “gel,” marking mentions of gels in various contexts.

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

    gel applications

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

    The neuron recognizes the word "gel" and related gel-based substances in scientific, cosmetic, and medical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    皛
    -2.98
    鰨
    -2.89
    le
    -2.89
    you
    -2.81
    狃
    -2.80
    迓
    -2.73
    灃
    -2.69
    ⼠
    -2.67
    bluza
    -2.61
    あります
    -2.56
    POSITIVE LOGITS
    ’
    2.91
    0
    2.66
     of
    2.50
    2
    2.41
    錵
    2.39
    的一個
    2.16
    他不
    2.14
    早已
    2.08
     pernikahan
    2.06
    >"+
    2.05
    Activations Density 0.020%

    No Known Activations