© 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. 121011
    Prev
    Next
    INDEX
    Explanations

    breaking up or regulating things

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

    effort, Claudius, student, me, impossibly, Western

    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
    位于
    0.48
    Type
    0.48
    約
    0.47
     характеризу
    0.45
    ighet
    0.45
    包含了
    0.45
    Το
    0.45
    包含
    0.44
    াবদ্ধ
    0.44
    ถ
    0.44
    POSITIVE LOGITS
     نظری
    0.46
     ương
    0.45
    داران
    0.45
    რებული
    0.45
    //}
    0.45
    لای
    0.45
    pinephrine
    0.44
    sière
    0.44
    ্লিশ
    0.43
    tní
    0.42
    Activations Density 0.000%

    No Known Activations