© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8773
    Prev
    Next
    INDEX
    Explanations

    dot followed by function

    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
    '.$
    0.64
    इस
    0.58
    >
    0.57
    是
    0.54
    ጨማሪ
    0.54
    >)
    0.53
    ख
    0.53
    一来
    0.53
    \%)
    0.52
    ‌ای
    0.52
    POSITIVE LOGITS
     rbuf
    0.58
     použív
    0.57
    刄
    0.57
    ethe
    0.54
    lige
    0.53
    Сма
    0.53
     cittam
    0.53
     うち
    0.52
     Gelegenheit
    0.52
    ంద
    0.52
    Activations Density 0.389%

    No Known Activations