© 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. 22090
    Prev
    Next
    INDEX
    Explanations

    events and gatherings

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

    . "* "

    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
    快速
    0.48
    虎
    0.46
     موسم
    0.46
    ي
    0.45
    肅
    0.44
     Tige
    0.43
    恐
    0.43
    ド
    0.43
    م
    0.42
    琿
    0.42
    POSITIVE LOGITS
    ates
    0.59
    ate
    0.55
    ute
    0.54
    appropriate
    0.53
    ante
    0.50
    antly
    0.50
    illation
    0.48
    urate
    0.48
    āl
    0.48
    landers
    0.47
    Activations Density 0.000%

    No Known Activations