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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 110509
    Prev
    Next
    INDEX
    Explanations

    code syntax elements

    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
     such
    -0.93
     tumbuhan
    -0.92
     feest
    -0.90
     Kräuter
    -0.90
     vervol
    -0.89
    UMES
    -0.87
     solches
    -0.87
     sogen
    -0.87
     čia
    -0.86
     такі
    -0.85
    POSITIVE LOGITS
     gustar
    1.07
     whether
    0.96
     "",
    0.95
    是否
    0.94
     MÉXICO
    0.91
    Westfalen
    0.88
     Légion
    0.88
     "-",
    0.88
    ajoz
    0.88
    woners
    0.88
    Activations Density 0.004%

    No Known Activations