© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 4788
    Prev
    Next
    INDEX
    Explanations

    what you encounter

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    s
    2.11
    সংখ্যক
    1.95
    sellers
    1.85
    ij
    1.76
    ively
    1.75
    ことになる
    1.73
    arity
    1.72
    ifiably
    1.72
    est
    1.71
    های
    1.71
    POSITIVE LOGITS
    𝗚
    2.16
    GAS
    2.02
    л
    2.00
    ە
    2.00
     وإن
    1.91
    الوجی
    1.91
    िका
    1.85
    𝗖
    1.84
     друзей
    1.84
    𝖊
    1.82
    Activations Density 0.043%

    No Known Activations