© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 258676
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    हीत
    0.51
    FBSDKSettings
    0.46
    ധ്യ
    0.46
     Fujita
    0.46
     मैदा
    0.46
     Đoàn
    0.46
     altera
    0.45
    瑗
    0.44
     chá
    0.44
    над
    0.44
    POSITIVE LOGITS
     ਤੁ
    0.52
     exos
    0.49
    ulier
    0.49
     ЗА
    0.47
     Экс
    0.47
     енер
    0.47
     up
    0.46
     ปี
    0.45
     ਲੋ
    0.45
     unrival
    0.45
    Activations Density 0.000%

    No Known Activations