© 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. 64265
    Prev
    Next
    INDEX
    Explanations

    documentary below, country , there is/was, photograph the, whose lease, directed for, Darkness auction

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

    organizational tree, byte offset

    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
    ب
    0.49
     تاکید
    0.47
    ك
    0.46
    س
    0.46
     کی
    0.45
    م
    0.45
     داری
    0.43
    de
    0.43
    نا
    0.43
     หน
    0.42
    POSITIVE LOGITS
    ерт
    0.47
    ைக்கு
    0.44
     crammed
    0.43
     ছাউ
    0.43
     жүктөө
    0.42
     পাকিস্তানের
    0.42
     Nilsson
    0.42
    憂
    0.42
     mw
    0.41
     çöze
    0.41
    Activations Density 0.000%

    No Known Activations