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. 8736
    Prev
    Next
    INDEX
    Explanations

    accidents and deaths

    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
     válvulas
    -0.81
     shooters
    -0.81
     thrilling
    -0.79
     expertly
    -0.77
    ليز
    -0.76
     unrelenting
    -0.76
    ulse
    -0.74
     combate
    -0.74
     venturing
    -0.73
     strange
    -0.72
    POSITIVE LOGITS
     crash
    1.09
    crash
    1.02
    Trag
    0.89
     tragedy
    0.88
    
    0.86
     tragic
    0.85
     fatalities
    0.85
     deaths
    0.84
    Killed
    0.84
     devast
    0.83
    Activations Density 0.030%

    No Known Activations