© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 11824
    Prev
    Next
    INDEX
    Explanations

    step or numbered list items

    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
    Negative Logits
    ال
    1.35
    ни
    1.34
    1
    1.26
    상
    1.20
    2
    1.19
    5
    1.19
    THING
    1.14
    7
    1.14
    हदी
    1.13
     a
    1.09
    POSITIVE LOGITS
    zelfde
    1.53
    P
    1.40
    in
    1.38
    ل
    1.36
    ే
    1.34
    ী
    1.27
    Invitrogen
    1.24
    ക്ക്
    1.20
    an
    1.17
    quela
    1.17
    Activations Density 0.088%

    No Known Activations