© 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. 202527
    Prev
    Next
    INDEX
    Explanations

    dashi, update, statue, change, service

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

    connecting items or ideas

    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
    观点
    0.50
    isection
    0.50
    ણા
    0.48
    espace
    0.48
     ইস্যুতে
    0.47
     আচ্ছা
    0.45
    ısından
    0.44
    诸
    0.44
     এক্ষেত্রে
    0.43
    vā
    0.43
    POSITIVE LOGITS
     accomp
    0.52
     acom
    0.51
     bort
    0.50
     noirâtres
    0.50
     nova
    0.50
     accompany
    0.49
     torches
    0.48
     produce
    0.48
     desc
    0.48
     horn
    0.48
    Activations Density 0.001%

    No Known Activations