© 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. 82877
    Prev
    Next
    INDEX
    Explanations

    Any order or refunds

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

    database structure and definitions

    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
    শস্ত্র
    0.47
    장이
    0.46
    یند
    0.46
    ینگ
    0.45
     anecd
    0.44
    پ
    0.44
     nondestructive
    0.44
     begg
    0.44
    कक्ष
    0.43
    ༞
    0.43
    POSITIVE LOGITS
     erklärte
    0.55
     ഗു
    0.52
     sagt
    0.50
     በላይ
    0.50
     erklärt
    0.49
     ગુ
    0.48
    ätz
    0.48
     čak
    0.46
    ských
    0.46
     Bürgermeister
    0.46
    Activations Density 0.000%

    No Known Activations