© 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. 153031
    Prev
    Next
    INDEX
    Explanations

    bless you as you

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

    than just

    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
     Comparisons
    0.49
    سٹم
    0.48
     Compar
    0.47
    Sockets
    0.47
     porówn
    0.46
    ي
    0.46
    compar
    0.46
     Translations
    0.46
     sockets
    0.45
    வனி
    0.45
    POSITIVE LOGITS
     thumb
    0.53
    ルメ
    0.50
    ܀
    0.50
     pursue
    0.48
     pursues
    0.48
    ,#
    0.46
    ,.
    0.46
     ん
    0.46
    marin
    0.43
    ,,
    0.43
    Activations Density 0.003%

    No Known Activations