© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 8749
    Prev
    Next
    INDEX
    Explanations

    model modelmodel weights

    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
    𝙤
    1.62
    𝙣
    1.55
    𝙡
    1.55
    𝙝
    1.46
    𝙖
    1.36
    𝙧
    1.33
     toDo
    1.32
    𝙪
    1.31
    ை
    1.31
     distractions
    1.22
    POSITIVE LOGITS
    берите
    1.27
    وق
    1.02
    matig
    1.01
    嶙
    1.00
    mere
    0.97
    정한
    0.95
    Artículo
    0.94
    इन
    0.94
     Emmett
    0.94
    fulness
    0.93
    Activations Density 0.052%

    No Known Activations