© 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. 10-GEMMASCOPE-RES-131K
    7. 59276
    Prev
    Next
    INDEX
    Explanations

    suits and garments

    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
    泔
    -2.17
     techniczne
    -1.85
    ují
    -1.81
     הם
    -1.80
    趼
    -1.74
    ндарт
    -1.73
     pembentukan
    -1.73
     keluarganya
    -1.69
     $\
    -1.68
    AutoresizingMask
    -1.68
    POSITIVE LOGITS
     It
    2.03
    闔
    1.99
    The
    1.90
    鏷
    1.87
     möglichen
    1.84
    ,
    1.83
     späteren
    1.73
    and
    1.73
     svol
    1.71
    y
    1.71
    Activations Density 0.007%

    No Known Activations