© 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. 199775
    Prev
    Next
    INDEX
    Explanations

    previously registered

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

    specific keywords and identifiers

    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
    ↵↵
    0.50
     февра
    0.48
     Мар
    0.48
     loan
    0.47
     увлека
    0.46
     concentra
    0.46
     двумя
    0.46
     ચ
    0.45
     investi
    0.45
     мар
    0.45
    POSITIVE LOGITS
    rées
    0.49
    坩
    0.49
    acuation
    0.47
    აკ
    0.47
    ਕ
    0.46
    सर्जन
    0.45
    ਨ੍ਹਾਂ
    0.45
    ارتی
    0.45
    alama
    0.45
    ตาย
    0.45
    Activations Density 0.001%

    No Known Activations