© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84098
    Prev
    Next
    INDEX
    Explanations

    web page structure

    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
    Outer
    -0.69
    Plain
    -0.69
    낸
    -0.69
    =>$
    -0.69
     estadio
    -0.67
    lanations
    -0.66
    влению
    -0.66
    Miller
    -0.66
     predicts
    -0.66
    Ellen
    -0.64
    POSITIVE LOGITS
    UTF
    0.73
     Samson
    0.71
    Licht
    0.70
    ندي
    0.69
     форми
    0.68
     мода
    0.68
    Decrease
    0.66
     Hild
    0.66
     рекоменду
    0.66
     lavora
    0.65
    Activations Density 0.047%

    No Known Activations