© 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. 108704
    Prev
    Next
    INDEX
    Explanations

    Juncker, general consensus

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

    advice and warnings

    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
     Provost
    0.53
     Caedwalla
    0.49
     रस
    0.49
    ปิด
    0.48
     দক্ষতার
    0.47
     Stalin
    0.46
     Tard
    0.46
    ۥ
    0.46
     закры
    0.46
     Tucker
    0.45
    POSITIVE LOGITS
    ುನ
    0.46
     divulgação
    0.46
    牛乳
    0.44
    몄
    0.43
    歉
    0.42
    ាប
    0.42
    chets
    0.41
    会社
    0.41
    本人
    0.41
    ঙ্গ
    0.40
    Activations Density 0.001%

    No Known Activations