© 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. 109739
    Prev
    Next
    INDEX
    Explanations

    arrest warrant issued

    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
     RULES
    -0.84
    RULES
    -0.76
     punte
    -0.75
     alér
    -0.74
    DialogComponent
    -0.73
    OWNER
    -0.73
    लब्
    -0.73
     sclero
    -0.71
    RECEIVE
    -0.71
    registro
    -0.70
    POSITIVE LOGITS
     warrant
    2.89
     warrants
    2.52
    warrant
    1.96
     issued
    1.85
     Warrant
    1.81
     issuance
    1.43
     WARRANT
    1.42
     issuing
    1.30
     Issued
    1.27
    Issued
    1.27
    Activations Density 0.019%

    No Known Activations