© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10326
    Prev
    Next
    INDEX
    Explanations

    handling text case

    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_22_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
    indsay
    0.99
    .$\
    0.86
    ลาคม
    0.85
     tỏ
    0.84
     exacting
    0.83
     Stiles
    0.82
    ixe
    0.80
    irts
    0.80
     Parnell
    0.79
    .$.
    0.77
    POSITIVE LOGITS
     변
    1.02
     범
    0.91
     지구
    0.85
    സില്‍
    0.83
     조합
    0.83
     인
    0.82
     окон
    0.82
     브
    0.82
     بقي
    0.82
     와
    0.82
    Activations Density 0.013%

    No Known Activations