© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 6904
    Prev
    Next
    INDEX
    Explanations

    before making

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lucr
    0.85
     nichts
    0.73
    vey
    0.73
     indes
    0.70
    ଯ
    0.69
    thats
    0.68
     ঝামে
    0.68
     şeyi
    0.67
    ＇
    0.67
     sighting
    0.67
    POSITIVE LOGITS
    Start
    0.82
     start
    0.80
     Start
    0.73
    Vg
    0.72
     commence
    0.70
    Ur
    0.69
    Decision
    0.69
     dic
    0.68
    start
    0.68
    スタート
    0.67
    Activations Density 0.002%

    No Known Activations