© 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. 118976
    Prev
    Next
    INDEX
    Explanations

    crash reporting and telemetry

    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
    üsseldorf
    -0.69
     盘
    -0.67
     áll
    -0.66
    ecute
    -0.66
     Ning
    -0.65
    EditMode
    -0.65
     vyk
    -0.65
    ຈ
    -0.64
    ofila
    -0.64
     overhaul
    -0.63
    POSITIVE LOGITS
     crash
    2.02
    Crash
    1.77
     Crash
    1.73
    crash
    1.65
     crashes
    1.52
     Cras
    1.38
     send
    1.31
     reporting
    1.30
     telemetry
    1.29
     feedback
    1.27
    Activations Density 0.072%

    No Known Activations