© 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. 70365
    Prev
    Next
    INDEX
    Explanations

    statements or explanations

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

    day to, within the, lot of

    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
     Chọn
    0.48
     কিংবা
    0.47
     അല്ലെങ്കിൽ
    0.46
    asını
    0.46
    ⲟ
    0.46
     或者
    0.45
     মিলিয়ন
    0.45
     минус
    0.45
     کھول
    0.44
    POSITIVE LOGITS
     in
    0.46
    ﺘ
    0.46
     to
    0.43
     reviving
    0.43
     an
    0.42
     splenic
    0.41
    SWE
    0.41
     reinvigor
    0.41
    CHICAGO
    0.41
    ﻌ
    0.40
    Activations Density 0.001%

    No Known Activations