© 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. 31-GEMMASCOPE-2-RES-16K
    7. 27
    Prev
    Next
    INDEX
    Explanations

    Instead of

    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_31_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     жөнүндө
    0.32
    0.32
     czyli
    0.31
     junto
    0.31
     любы
    0.29
    schein
    0.29
     zodat
    0.29
     メーカー
    0.28
     Untuk
    0.28
     சற்று
    0.28
    POSITIVE LOGITS
    <unused2197>
    0.46
    <unused2169>
    0.39
    <unused2222>
    0.35
    <unused2204>
    0.33
    <unused2157>
    0.33
    䏹
    0.32
    َا
    0.30
     of
    0.29
    antly
    0.29
    స్
    0.29
    Activations Density 6.852%

    No Known Activations