© 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. 3802
    Prev
    Next
    INDEX
    Explanations

    Mendeleev, Gemma, Bile, Syaoran, Fulfill, Barty

    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
    et
    1.43
    ud
    1.32
    ש
    1.29
    ס
    1.25
    and
    1.23
    ي
    1.23
    ya
    1.21
    ce
    1.13
    ال
    1.13
    س
    1.09
    POSITIVE LOGITS
    ৯
    1.40
     ومع
    1.23
    を有
    1.23
    ுள்ளனர்
    1.08
    mobilpay
    1.04
    ৭
    1.03
    ます
    1.01
    𝖾
    0.95
    を取
    0.95
     inconsist
    0.94
    Activations Density 0.420%

    No Known Activations