© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 37753
    Prev
    Next
    INDEX
    Explanations

    script headers or code lines

    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
     sundown
    -0.76
    城主
    -0.73
    するのは
    -0.73
    曖昧さ
    -0.73
    Napoleon
    -0.72
    なくても
    -0.71
    ディション
    -0.71
    することは
    -0.71
    自由に
    -0.71
     Alonzo
    -0.70
    POSITIVE LOGITS
    沸
    0.83
     này
    0.82
     court
    0.81
    院
    0.81
     clan
    0.76
    ThroughAttribute
    0.76
     palace
    0.75
     ví
    0.75
     буд
    0.75
     Dauer
    0.75
    Activations Density 0.021%

    No Known Activations