© 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. 118816
    Prev
    Next
    INDEX
    Explanations

    interrupted

    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
    tahui
    -0.82
     hefyd
    -0.73
     mobilization
    -0.71
    ícone
    -0.70
    otel
    -0.68
    饋
    -0.68
    人員
    -0.67
    licts
    -0.66
     after
    -0.65
    veloppe
    -0.65
    POSITIVE LOGITS
     interrupt
    4.50
     interrupted
    4.25
     interrupting
    4.13
     interrupts
    4.06
     Interrupt
    3.88
     interruption
    3.80
    interrupt
    3.78
     interruptions
    3.61
    Interrupt
    3.53
    interrupted
    3.17
    Activations Density 0.014%

    No Known Activations