© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 191792
    Prev
    Next
    INDEX
    Explanations

    actions related to 'interruption'

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

    interpret and inter-

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    in
    0.90
    ong
    0.68
    en
    0.67
    h
    0.63
    ↵↵
    0.61
    </h2>
    0.60
     of
    0.59
    的确
    0.59
     verwend
    0.58
     amely
    0.58
    POSITIVE LOGITS
     intercepts
    0.95
    Intercept
    0.87
     인터
    0.85
    INTER
    0.83
     intér
    0.77
     intersects
    0.76
     intercept
    0.75
     INTER
    0.73
     интер
    0.73
     intervent
    0.71
    Activations Density 0.056%

    No Known Activations