© 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. 2935
    Prev
    Next
    INDEX
    Explanations

    UK border, networking sites, dyeing company

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

    file operations, palindromes, skills

    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
    ွ
    0.17
    데이터
    0.17
    𝐮
    0.17
     sécurité
    0.17
    ུ་
    0.16
     পরিষেবা
    0.16
     setShow
    0.16
     кеңсесинде
    0.16
    োষণ
    0.15
     নেবে
    0.15
    POSITIVE LOGITS
    ,
    0.22
    stressed
    0.18
    YLE
    0.18
    yai
    0.17
     まず
    0.17
     মতে
    0.16
     tossed
    0.16
     wholeheartedly
    0.16
     passionately
    0.16
    likle
    0.16
    Activations Density 0.016%

    No Known Activations