© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91006
    Prev
    Next
    INDEX
    Explanations

    May not, actually expected, understanding, besides reducing

    np_acts-logits-general · gemini-2.5-flash-lite

    don't just list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     dingin
    0.46
    physiological
    0.43
    ,
    0.42
    '
    0.41
     ustedes
    0.40
     付き
    0.40
     ===
    0.40
     kalian
    0.39
     of
    0.39
     appunto
    0.39
    POSITIVE LOGITS
    餑
    0.48
     बढ़ता
    0.47
    粨
    0.46
     ভারতের
    0.44
     использование
    0.44
     وفق
    0.42
     сокра
    0.42
    缩
    0.42
     বাড়বে
    0.42
    ଗ
    0.42
    Activations Density 0.004%

    No Known Activations