© 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. 15226
    Prev
    Next
    INDEX
    Explanations

    it seems

    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
     and
    -2.38
     as
    -2.25
     in
    -1.95
     although
    -1.95
     such
    -1.79
     from
    -1.77
     since
    -1.77
     while
    -1.69
     to
    -1.68
    --;
    -1.61
    POSITIVE LOGITS
    Dette
    1.69
    7
    1.68
    ейчас
    1.65
     Permite
    1.65
    вгений
    1.63
    Hvis
    1.63
     mojej
    1.63
     estadia
    1.61
     Fácil
    1.59
     surtido
    1.56
    Activations Density 0.120%

    No Known Activations