© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 241152
    Prev
    Next
    INDEX
    Explanations

    there to meet

    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
     richesse
    0.49
     ለ
    0.49
     fistule
    0.48
    naie
    0.47
    ;/
    0.47
     paris
    0.47
     intelectual
    0.47
     засе
    0.47
     réponse
    0.47
     решение
    0.46
    POSITIVE LOGITS
    الات
    0.50
    するか
    0.49
    خص
    0.46
    一部
    0.46
    а
    0.45
    艾
    0.45
    ラ
    0.44
    oldCount
    0.44
    放射
    0.44
    菲
    0.43
    Activations Density 0.001%

    No Known Activations