© 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. 235513
    Prev
    Next
    INDEX
    Explanations

    proudly powered, made in

    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
     be
    0.47
    ıl
    0.46
    Setting
    0.46
    ット
    0.46
    Laurie
    0.46
    Reply
    0.45
    t
    0.45
    名
    0.45
    It
    0.44
    page
    0.44
    POSITIVE LOGITS
    來越
    0.49
     Rein
    0.49
     ciências
    0.46
    科學
    0.46
     variabel
    0.45
     ಸಾಕ
    0.45
     YANG
    0.45
    鳍
    0.45
    嶇
    0.45
    ivät
    0.44
    Activations Density 0.001%

    No Known Activations