© 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. 14420
    Prev
    Next
    INDEX
    Explanations

    boolean false values

    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
     of
    -1.89
     I
    -1.77
    -
    -1.68
     we
    -1.66
    みたいに
    -1.60
     my
    -1.57
     i
    -1.50
     o
    -1.50
     outras
    -1.46
     presque
    -1.44
    POSITIVE LOGITS
    there
    1.50
    voltaic
    1.50
     Jér
    1.48
    Surprisingly
    1.46
     Holanda
    1.46
    ثم
    1.45
    瀧
    1.45
    jących
    1.44
    However
    1.43
     為
    1.43
    Activations Density 0.007%

    No Known Activations