© 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. 99262
    Prev
    Next
    INDEX
    Explanations

    html document structure

    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
     vimos
    -1.88
    硖
    -1.87
     its
    -1.87
     już
    -1.86
     hicimos
    -1.80
     it
    -1.77
    czerw
    -1.74
     permitan
    -1.73
    炝
    -1.70
    italien
    -1.66
    POSITIVE LOGITS
    THE
    1.88
    It
    1.85
    \
    1.79
    あの
    1.74
    THERE
    1.70
    外国
    1.69
    гите
    1.65
     entire
    1.65
    also
    1.64
    //
    1.61
    Activations Density 0.026%

    No Known Activations