© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 432
    Prev
    Next
    INDEX
    Explanations

    Ken Thompson

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_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
    м
    0.66
    ar
    0.66
    is
    0.66
    टोन
    0.65
    u
    0.63
     bergerak
    0.63
     berwarna
    0.62
    tiny
    0.62
    ো
    0.61
    undred
    0.61
    POSITIVE LOGITS
     theseKeys
    0.90
    ExpNow
    0.88
    Dijstra
    0.86
     andRow
    0.86
     谢
    0.86
     低
    0.85
     木
    0.84
     리뷰
    0.84
     你
    0.83
     不
    0.83
    Activations Density 1.146%

    No Known Activations