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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 5998
    Prev
    Next
    INDEX
    Explanations

    mid-

    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
    j
    2.38
    ae
    2.30
    vv
    2.27
    ง
    2.23
    র
    2.14
    illä
    2.11
    čně
    2.11
    ā
    2.11
    다
    2.08
    ä
    2.06
    POSITIVE LOGITS
    岖
    2.19
    ного
    2.17
    であり
    2.05
    ной
    1.95
    ไม่ใช่
    1.92
    ありません
    1.89
    缀
    1.88
    を有
    1.78
    であれば
    1.77
    を持ち
    1.77
    Activations Density 0.013%

    No Known Activations