© 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. 133625
    Prev
    Next
    INDEX
    Explanations

    setting character set

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

    character set specifications

    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
    9
    0.72
    6
    0.71
    3
    0.64
    4
    0.63
    Р
    0.57
    5
    0.56
    8
    0.55
    一些
    0.52
    ل
    0.52
    一共
    0.52
    POSITIVE LOGITS
     language
    0.61
     भाषा
    0.59
     langue
    0.55
     CHARSET
    0.54
     lingua
    0.53
     Bahasa
    0.52
     languages
    0.52
     bahasa
    0.52
     statusCode
    0.50
     langage
    0.50
    Activations Density 0.000%

    No Known Activations