© 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. 78237
    Prev
    Next
    INDEX
    Explanations

    renovation, impression, Copy, Derechos

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

    fight against, Identification was, How Foods, integrity mechanisms, potentially padding, Why Pages

    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
     Qi
    0.52
     v
    0.52
     Po
    0.52
     G
    0.50
     M
    0.49
     H
    0.48
     Chick
    0.48
     X
    0.48
     Jin
    0.48
     Phrase
    0.48
    POSITIVE LOGITS
    预防
    0.58
    Tambah
    0.54
    ᆭ
    0.53
     entferne
    0.50
    柽
    0.50
     کبھی
    0.49
     документів
    0.49
     отриму
    0.49
     tehdä
    0.48
     мате
    0.48
    Activations Density 0.002%

    No Known Activations