© 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. 149052
    Prev
    Next
    INDEX
    Explanations

    Telegram bot and support hotline

    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
    葳
    0.69
     downward
    0.67
    ǀ
    0.67
    avl
    0.67
     እየሱስ
    0.67
     compañero
    0.66
    ey
    0.66
    ávez
    0.65
     nomenclatura
    0.65
    ABET
    0.64
    POSITIVE LOGITS
    ongoing
    0.69
     कुर्ता
    0.66
     Ongoing
    0.65
    Ongoing
    0.65
    Следу
    0.65
     Oni
    0.64
     stripper
    0.61
    ?}
    0.60
    ларын
    0.60
    ოკ
    0.59
    Activations Density 0.001%

    No Known Activations