© 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. 14137
    Prev
    Next
    INDEX
    Explanations

    words starting with "all"

    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
     all
    1.08
    latitude
    1.08
    पर्य
    1.05
     πυ
    1.00
     contrasting
    1.00
    ทั้งหมด
    1.00
     arg
    0.98
    贾
    0.96
    り
    0.96
    οι
    0.92
    POSITIVE LOGITS
    ergic
    1.67
    igator
    1.52
     ello
    1.44
    igators
    1.43
     demás
    1.43
    iances
    1.42
    erdings
    1.38
    llllll
    1.31
    usions
    1.31
    llllllll
    1.30
    Activations Density 0.032%

    No Known Activations