© 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. 236983
    Prev
    Next
    INDEX
    Explanations

    provided by

    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
     Posting
    0.46
    鼐
    0.44
     Virology
    0.44
     seni
    0.43
    lai
    0.42
     Morin
    0.42
    lL
    0.41
     Pilots
    0.41
    )<
    0.40
    []');
    0.40
    POSITIVE LOGITS
     要素
    0.57
     イン
    0.53
     設定
    0.53
    誤
    0.51
     recurs
    0.50
     éléments
    0.49
     espagn
    0.49
     กำ
    0.49
    電影
    0.49
     француз
    0.49
    Activations Density 0.001%

    No Known Activations