© 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. 106424
    Prev
    Next
    INDEX
    Explanations

    ability to do

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

    major points/ideas

    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
    Not in Any Lists

    No Comments

    Negative Logits
    搆
    0.45
     Hez
    0.42
    يير
    0.41
     kree
    0.40
    צת
    0.40
     Vara
    0.40
     arrhyth
    0.40
     vara
    0.40
     courageous
    0.40
     certi
    0.40
    POSITIVE LOGITS
    ob
    0.54
    ág
    0.53
    rás
    0.52
     例
    0.52
    ímenes
    0.52
     提供
    0.51
     শ্রীমতি
    0.50
    antes
    0.50
    obj
    0.49
    自体
    0.49
    Activations Density 0.000%

    No Known Activations