© 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. 3171
    Prev
    Next
    INDEX
    Explanations

    UFC

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

    parentheses and variables

    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
    <unused86>
    0.34
    ဘူး
    0.33
    <unused80>
    0.32
     আনুশকা
    0.32
    ارات
    0.31
     évén
    0.31
     تھیں
    0.31
    ChatItem
    0.31
    篑
    0.31
     সংখ্যা
    0.31
    POSITIVE LOGITS
    which
    0.51
    któ
    0.49
    ˒
    0.49
    whose
    0.46
    un
    0.46
     which
    0.45
     ওরফে
    0.43
    that
    0.43
    ל
    0.42
     и
    0.42
    Activations Density 0.189%

    No Known Activations