© 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. 17-GEMMASCOPE-2-RES-16K
    7. 10564
    Prev
    Next
    INDEX
    Explanations

    least one or quantity

    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_17_width_16k_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
    িন
    1.71
    它
    1.71
    л
    1.69
     hordes
    1.64
    েন
    1.62
     incumbent
    1.61
    ,*/}*.
    1.60
     dwind
    1.59
    다
    1.55
     glory
    1.54
    POSITIVE LOGITS
    পক্ষে
    2.28
    aurant
    1.87
     Temos
    1.82
    ژی
    1.75
    ႈ
    1.67
    🅽
    1.61
    伍
    1.61
    na
    1.59
    sman
    1.54
    langan
    1.52
    Activations Density 0.042%

    No Known Activations