© 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. 217855
    Prev
    Next
    INDEX
    Explanations

    said that, parts of, enrolled agents

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

    patterns and concepts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ‌آ
    0.49
    ع
    0.48
    considering
    0.46
    may
    0.46
     می‌ده
    0.46
     ہو
    0.44
    خل
    0.44
    ಅ
    0.42
    ड़क
    0.42
    May
    0.41
    POSITIVE LOGITS
    
    0.46
     coordinador
    0.46
     Kraj
    0.44
     setInterval
    0.44
     möglichst
    0.43
     supprimer
    0.42
     изго
    0.42
     রং
    0.42
     столько
    0.41
     positional
    0.41
    Activations Density 0.000%

    No Known Activations