© 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. 157452
    Prev
    Next
    INDEX
    Explanations

    or

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

    listing alternatives

    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
    kuje
    0.53
    ３
    0.50
     ਦਵਾਈ
    0.50
    ließt
    0.49
     μεγά
    0.47
    主に
    0.46
     крова
    0.46
     два
    0.46
     głównie
    0.46
     большой
    0.46
    POSITIVE LOGITS
     ataupun
    0.70
     alebo
    0.67
    或者是
    0.67
     hoặc
    0.59
    或
    0.58
    或者
    0.57
     अथवा
    0.56
     või
    0.56
     किंवा
    0.55
     లేదా
    0.55
    Activations Density 0.001%

    No Known Activations