© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31959
    Prev
    Next
    INDEX
    Explanations

    IGraphicsBegin

    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_34/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
     absch
    -0.77
     searches
    -0.70
    lanti
    -0.69
    search
    -0.68
    одно
    -0.65
    mathscr
    -0.64
     poursuite
    -0.64
     عوض
    -0.63
    Search
    -0.63
     Search
    -0.62
    POSITIVE LOGITS
     />';
    0.76
     Publisher
    0.74
     Pinnacle
    0.73
    vierten
    0.73
    位的
    0.69
     Функ
    0.68
     ")");
    0.67
    겼
    0.66
    andas
    0.66
     разум
    0.66
    Activations Density 0.108%

    No Known Activations