© 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. 22-GEMMASCOPE-RES-131K
    7. 25879
    Prev
    Next
    INDEX
    Explanations

    government agencies and regulatory bodies

    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_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
    𖣔
    -1.03
    논
    -0.97
     され
    -0.95
    esperienza
    -0.95
    𓍊
    -0.94
     bí
    -0.94
    鎵
    -0.94
     quidem
    -0.93
     économ
    -0.93
    ègre
    -0.93
    POSITIVE LOGITS
     what
    1.10
     how
    1.09
     who
    1.05
     because
    0.99
     approved
    0.96
     through
    0.92
     学生
    0.91
    턴
    0.90
    着脸
    0.90
     there
    0.89
    Activations Density 0.088%

    No Known Activations