© 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. 226695
    Prev
    Next
    INDEX
    Explanations

    quality control

    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
    食
    0.48
    ケット
    0.46
    対応
    0.46
    コース
    0.46
    際に
    0.46
    カルシ
    0.45
    サイズ
    0.45
    攻撃
    0.44
    後面
    0.44
    例えば
    0.43
    POSITIVE LOGITS
    门户
    0.48
    㵄
    0.48
    suppliers
    0.47
    erche
    0.47
     إنشاء
    0.46
     बढ़ते
    0.46
    beri
    0.45
    lägt
    0.45
    borough
    0.44
     Spending
    0.44
    Activations Density 0.001%

    No Known Activations