© 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-65K
    7. 678
    Prev
    Next
    INDEX
    Explanations

    publicly available for

    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_65k_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
     (
    0.86
    (
    0.85
    0.78
    /
    0.75
     [
    0.67
     considered
    0.67
     Assumptions
    0.64
     PC
    0.63
     Med
    0.62
     Tri
    0.60
    POSITIVE LOGITS
     gamanam
    0.83
    𒀝
    0.79
     berlang
    0.78
    webhook
    0.78
     namani
    0.78
     Стаўкі
    0.76
    鈈
    0.75
    cellSize
    0.73
    𒌇
    0.73
    ࢮ
    0.73
    Activations Density 0.267%

    No Known Activations