© 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. 205315
    Prev
    Next
    INDEX
    Explanations

    strong and soft

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

    lists and structured text

    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
    徜
    0.49
    ジオ
    0.46
    ンド
    0.45
    のない
    0.44
    近
    0.43
    อฟ
    0.43
    ショナル
    0.43
     dash
    0.43
     दिवा
    0.43
    घ
    0.43
    POSITIVE LOGITS
     வேலை
    0.50
     Цер
    0.49
    র্পণ
    0.48
    thouse
    0.47
     változat
    0.47
     tặng
    0.47
    ların
    0.46
    orche
    0.46
    uterine
    0.46
     deducted
    0.45
    Activations Density 0.001%

    No Known Activations