Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8739
    Prev
    Next
    INDEX
    Explanations

    PHP code and file paths

    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
     valsty
    -0.82
     Hered
    -0.81
     FAV
    -0.79
    ESCAPE
    -0.78
     Hawkes
    -0.77
    المكان
    -0.75
     yan
    -0.75
    umán
    -0.74
    utuhan
    -0.74
    出来ました
    -0.73
    POSITIVE LOGITS
     Americans
    0.84
    enderror
    0.81
    oneofs
    0.78
     Corresponding
    0.74
     ソ
    0.73
     reflections
    0.73
    Ɔ
    0.73
     Windows
    0.73
     valued
    0.71
    ernas
    0.71
    Activations Density 0.004%

    No Known Activations