© 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. 29-GEMMASCOPE-2-RES-262K
    7. 149432
    Prev
    Next
    INDEX
    Explanations

    providing reasoning

    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_29_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
     plumage
    0.77
    rodní
    0.75
     weapons
    0.75
    少ない
    0.70
    砍
    0.69
     ראש
    0.68
    وما
    0.67
    拯
    0.66
    sender
    0.65
     huid
    0.65
    POSITIVE LOGITS
    😬
    0.87
    ing
    0.85
     Taking
    0.84
    😳
    0.78
    !).
    0.77
     Took
    0.77
    Token
    0.77
    😄
    0.76
    ப்போது
    0.75
     ഔ
    0.75
    Activations Density 0.003%

    No Known Activations