© 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. 7251
    Prev
    Next
    INDEX
    Explanations

    SQL CREATE INDEX

    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
    aty
    1.29
    ла
    1.23
    onial
    1.19
    ain
    1.17
    ol
    1.16
    atio
    1.16
    .
    1.13
    atis
    1.11
    ops
    1.10
    ement
    1.09
    POSITIVE LOGITS
    ير
    1.61
    gène
    1.49
    ছেন
    1.46
    서
    1.36
    ード
    1.35
    сть
    1.34
    goài
    1.34
    ารย์
    1.34
    ται
    1.33
    お子
    1.33
    Activations Density 0.000%

    No Known Activations