© 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. 92490
    Prev
    Next
    INDEX
    Explanations

    innocent unless, Alhambra palace

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

    local advertising

    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
     ενεργ
    0.49
     α
    0.48
    ’)
    0.48
    戙
    0.48
     الآن
    0.47
     έχ
    0.46
     tượng
    0.46
     λα
    0.46
     κάν
    0.45
     ഇപ്പോൾ
    0.45
    POSITIVE LOGITS
    遭遇
    0.47
    établissement
    0.45
    晦
    0.45
    ذكر
    0.43
    }}
    0.42
    തി
    0.42
    /">
    0.42
    トラブル
    0.42
    судар
    0.41
    Ն
    0.41
    Activations Density 0.000%

    No Known Activations