© 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. 10-GEMMASCOPE-RES-131K
    7. 102270
    Prev
    Next
    INDEX
    Explanations

    people's roles and professions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ците
    -1.31
    我觉得
    -1.29
    endDate
    -1.29
    Eleven
    -1.17
    }")]
    -1.15
    Править
    -1.14
    بعض
    -1.13
    Another
    -1.11
     various
    -1.08
     робо
    -1.08
    POSITIVE LOGITS
    ラックス
    1.11
    such
    1.09
     MOST
    1.08
    until
    1.07
    目光
    1.06
    但在
    1.05
     anticipo
    1.05
     queste
    1.04
    ほんと
    1.03
     probablement
    1.02
    Activations Density 0.154%

    No Known Activations