Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7569
    Prev
    Next
    INDEX
    Explanations

    foreign language content

    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_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
    aing
    1.38
    a
    1.28
    in
    1.24
    el
    1.17
     torchvision
    1.12
    at
    1.09
     ∑
    1.08
    eliness
    1.08
     किरा
    1.08
    em
    1.07
    POSITIVE LOGITS
    रोवर
    1.31
    denly
    1.29
    های
    1.21
    هایی
    1.21
    জীব
    1.20
     अधिकारी
    1.20
     brengen
    1.15
    とめ
    1.15
    ㅢ
    1.12
    حه
    1.11
    Activations Density 0.000%

    No Known Activations