© 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. 59231
    Prev
    Next
    INDEX
    Explanations

    out to, response that, cut out, speak 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
     "
    -2.11
     by
    -1.75
     '
    -1.67
     if
    -1.62
     если
    -1.59
     in
    -1.51
    Why
    -1.51
     If
    -1.49
    Are
    -1.48
     you
    -1.45
    POSITIVE LOGITS
     vatten
    1.59
     kvä
    1.53
     their
    1.48
     liknande
    1.48
     påver
    1.48
     hjälp
    1.48
     berätt
    1.47
    に近い
    1.46
     arbeta
    1.45
    也會
    1.44
    Activations Density 0.082%

    No Known Activations