© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2298
    Prev
    Next
    INDEX
    Explanations

    about me here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ресень
    0.48
     листопада
    0.46
     irgende
    0.43
    eraient
    0.43
    TempBuffer
    0.40
    лл
    0.39
     знать
    0.39
     것처럼
    0.38
    尌
    0.38
    ціа
    0.37
    POSITIVE LOGITS
     and
    0.55
     અને
    0.51
     below
    0.50
     এবং
    0.48
     و
    0.47
     και
    0.47
     detailed
    0.46
     +
    0.45
     и
    0.45
     বিস্তারিত
    0.45
    Activations Density 0.009%

    No Known Activations