© 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. 113755
    Prev
    Next
    INDEX
    Explanations

    webfont.eot, Ruger, Correlation, Lori

    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
     '
    -2.44
     &
    -2.39
     imidlertid
    -2.08
     \
    -2.06
     betale
    -2.05
     perhaps
    -2.03
     {
    -2.03
     or
    -1.99
     those
    -1.99
     prioridades
    -1.98
    POSITIVE LOGITS
    沵
    2.78
    𓆜
    2.70
    逦
    2.59
    They
    2.53
    <<"
    2.44
    有种
    2.39
    は
    2.38
    薷
    2.34
    We
    2.33
    {
    2.33
    Activations Density 0.000%

    No Known Activations