© 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. 59235
    Prev
    Next
    INDEX
    Explanations

    don't want to

    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
     alza
    -2.09
    ဴ
    -2.03
     ähnlichen
    -2.00
     Fällen
    -1.96
    ⎆
    -1.95
     still
    -1.94
    خصص
    -1.91
     verbess
    -1.91
    ㊗
    -1.91
     logró
    -1.84
    POSITIVE LOGITS
     moim
    2.22
     podoba
    1.94
    mamp
    1.94
     هیچ
    1.92
     redak
    1.91
    {
    1.84
     you
    1.84
     of
    1.80
    啻
    1.79
    _{
    1.75
    Activations Density 0.007%

    No Known Activations