© 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. 33109
    Prev
    Next
    INDEX
    Explanations

    programming code and licenses

    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
    ∵
    -0.82
     innovación
    -0.69
     Kurz
    -0.68
     ν
    -0.67
     requires
    -0.66
    embley
    -0.66
    돋
    -0.66
    <?>
    -0.65
     cus
    -0.64
     Zero
    -0.64
    POSITIVE LOGITS
    ély
    0.84
    шан
    0.77
    umption
    0.77
     Communauté
    0.74
     dommage
    0.73
    ząt
    0.72
     appré
    0.72
     trasp
    0.71
    license
    0.69
    cée
    0.68
    Activations Density 0.046%

    No Known Activations