© 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. 75951
    Prev
    Next
    INDEX
    Explanations

    self-explanatory phrases

    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
    思议
    -0.69
    rifft
    -0.69
     Mid
    -0.69
    県道
    -0.68
     Leroy
    -0.68
    ROZ
    -0.67
    wydd
    -0.67
    アンサー
    -0.66
    칫
    -0.66
     Palmer
    -0.65
    POSITIVE LOGITS
    自
    0.93
    옛
    0.87
     自
    0.79
     soñ
    0.75
    🍔
    0.75
     invented
    0.74
    TextSpan
    0.74
     abolished
    0.74
    ceptos
    0.74
     synes
    0.73
    Activations Density 0.020%

    No Known Activations