© 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. 14660
    Prev
    Next
    INDEX
    Explanations

    directory paths ending in index.htm

    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
    ম্ব
    0.61
    subtract
    0.56
     sinh
    0.56
     ferm
    0.55
    --;
    0.53
    oming
    0.52
     defens
    0.52
    置
    0.52
     hata
    0.52
    ।--
    0.52
    POSITIVE LOGITS
     După
    0.72
     několik
    0.69
     jakiś
    0.67
     ม
    0.66
     حداقل
    0.65
     Educación
    0.65
    ങ്കിലും
    0.64
     Aş
    0.64
    inguém
    0.64
    ﮕ
    0.64
    Activations Density 0.000%

    No Known Activations