© 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. 80932
    Prev
    Next
    INDEX
    Explanations

    of organizations

    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
    ع
    0.53
    ду
    0.48
    い
    0.47
    و
    0.46
    这
    0.46
     當
    0.45
    當
    0.45
    結構
    0.44
    人們
    0.44
    人類
    0.43
    POSITIVE LOGITS
     figlia
    0.49
     invested
    0.46
     Parisian
    0.46
     निरीक्षक
    0.46
    ಂಕ್
    0.45
    ongrass
    0.45
     intitulé
    0.45
    socketList
    0.44
     overlying
    0.44
    iolet
    0.44
    Activations Density 0.001%

    No Known Activations