© 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. 120859
    Prev
    Next
    INDEX
    Explanations

    Temp range, life time

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

    list items, descriptions, or code snippets

    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
    ब
    0.52
    प
    0.45
    బ
    0.43
    জ
    0.43
    তেন
    0.42
    বর্তমান
    0.40
     Dene
    0.40
    স
    0.39
     Figures
    0.39
     Responses
    0.39
    POSITIVE LOGITS
     dieta
    0.51
     اینجا
    0.49
     અથવા
    0.49
     יכול
    0.48
    ことも
    0.47
     pavattati
    0.46
     diminue
    0.46
    wości
    0.45
     ハンド
    0.45
     wygod
    0.45
    Activations Density 0.001%

    No Known Activations