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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 35773
    Prev
    Next
    INDEX
    Explanations

    inline styles or code

    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
    ера
    1.68
    й
    1.67
    ي
    1.53
    йы
    1.48
    ă
    1.47
     LE
    1.43
    ет
    1.41
     Кли
    1.40
    ﺎ
    1.40
     А
    1.35
    POSITIVE LOGITS
    le
    2.33
    on
    1.88
    ください
    1.88
    ség
    1.88
    ak
    1.79
    en
    1.72
    c
    1.72
    تمل
    1.62
     essentielles
    1.57
    志愿
    1.50
    Activations Density 0.002%

    No Known Activations