© 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. 109839
    Prev
    Next
    INDEX
    Explanations

    accidents, threats, disease, drought

    np_acts-logits-general · gemini-2.5-flash-lite

    lists of hazards, risks, or dangerous conditions, especially when separated by commas.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     بندی
    -0.81
    Penalty
    -0.77
     Yesterday
    -0.76
    ㄦ
    -0.73
    たっぷり
    -0.73
    世話
    -0.72
     JC
    -0.72
     möjligt
    -0.72
     Oc
    -0.71
    Hurt
    -0.70
    POSITIVE LOGITS
     governmental
    1.10
     war
    1.07
     acts
    1.05
     naturali
    0.94
     enemy
    0.92
     fire
    0.90
    governmental
    0.89
    政府
    0.88
    iological
    0.88
     guerra
    0.88
    Activations Density 0.014%

    No Known Activations