© 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. 9-GEMMASCOPE-2-RES-16K
    7. 35
    Prev
    Next
    INDEX
    Explanations

    supply chain

    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_9_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
    Z
    0.93
    Y
    0.91
    I
    0.89
    ନ୍ଦ
    0.85
    П
    0.81
    Л
    0.76
    H
    0.73
    L
    0.73
    D
    0.73
    UP
    0.72
    POSITIVE LOGITS
    <unused702>
    0.77
     می‌دهد
    0.69
    ‌ای
    0.68
    
    0.68
    \}.
    0.67
     ∗
    0.67
     dla
    0.66
    <unused27>
    0.66
     boutique
    0.66
     שב
    0.66
    Activations Density 6.512%

    No Known Activations