© 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. 142275
    Prev
    Next
    INDEX
    Explanations

    Panel, function, face, or geometric shapes

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

    code snippet

    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
    eced
    0.54
    臧
    0.52
     денег
    0.51
     вышел
    0.46
    花的
    0.45
    牲
    0.44
     पैसों
    0.44
    慰
    0.43
    萱
    0.43
    किस
    0.43
    POSITIVE LOGITS
     lagoon
    0.58
     탐
    0.52
     ক্ষেত্র
    0.52
     rectangle
    0.47
     concentric
    0.46
    鲔
    0.46
     rectangles
    0.45
     연속
    0.44
    рую
    0.44
    رافی
    0.44
    Activations Density 0.000%

    No Known Activations