© 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. 40-GEMMASCOPE-2-RES-16K
    7. 8223
    Prev
    Next
    INDEX
    Explanations

    expression or statement

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

    expressions and statements

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Rap
    0.47
    ガラス
    0.43
    carry
    0.43
    rap
    0.42
    けん
    0.42
    วัล
    0.42
    несен
    0.41
    鹸
    0.41
    rubber
    0.41
    孅
    0.41
    POSITIVE LOGITS
     expression
    0.88
     Expression
    0.84
     expr
    0.80
     expressions
    0.79
    表达式
    0.75
    expression
    0.74
    Expression
    0.74
    expr
    0.72
     STATEMENT
    0.71
     выражение
    0.71
    Activations Density 0.016%

    No Known Activations