© 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. 250529
    Prev
    Next
    INDEX
    Explanations

    end celebration

    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
    Negative Logits
     တ
    0.48
     second
    0.47
     δεύτε
    0.46
     Second
    0.46
     subdivided
    0.46
     Locator
    0.46
     seconda
    0.45
     す
    0.45
     considère
    0.45
     considéré
    0.45
    POSITIVE LOGITS
    ్రో
    0.50
     kiri
    0.49
    呼
    0.48
    dlj
    0.47
     Dmitry
    0.46
     plak
    0.46
    فت
    0.45
    हुल
    0.45
    зова
    0.45
    مو
    0.45
    Activations Density 0.001%

    No Known Activations