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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 82786
    Prev
    Next
    INDEX
    Explanations

    potency and stringency

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

    scientific terms ending in "-potency," "-stringency," or "-otency" that relate to biological and chemical properties.

    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_34/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
     CPI
    -0.77
     endIndex
    -0.73
    isNumber
    -0.70
     Buc
    -0.69
    atung
    -0.69
    닝
    -0.69
     PMA
    -0.68
     Access
    -0.68
    INTR
    -0.68
     beware
    -0.68
    POSITIVE LOGITS
    ency
    1.43
    ient
    1.23
     potency
    1.16
    ent
    1.09
    ently
    0.99
    gent
    0.93
     Pot
    0.90
    iency
    0.88
    ancy
    0.85
     stringent
    0.83
    Activations Density 0.056%

    No Known Activations