© 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. 166767
    Prev
    Next
    INDEX
    Explanations

    list items or structure

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

    create new app or project

    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
     the
    0.51
     claimed
    0.47
     Claim
    0.46
     Mohawk
    0.46
     in
    0.46
    ↵
    0.46
     Brink
    0.44
    the
    0.44
     claims
    0.44
     County
    0.43
    POSITIVE LOGITS
     querer
    0.59
     細胞
    0.57
     عاملين
    0.54
     느낌
    0.54
    同學們
    0.51
    याँ
    0.51
     مکمل
    0.51
    潙
    0.51
     چاہتے
    0.50
    電荷
    0.50
    Activations Density 0.001%

    No Known Activations