© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 29298
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

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

    addressing issues and control

    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
    posto
    0.42
    ствовал
    0.39
     enjoyable
    0.38
     נישט
    0.38
     않습니다
    0.37
    шон
    0.37
    璟
    0.37
    ше
    0.37
    ひとつ
    0.37
    зов
    0.36
    POSITIVE LOGITS
     LeBron
    0.42
     pią
    0.39
     Notepad
    0.39
    myn
    0.38
    >>;
    0.38
    {(\
    0.38
     Negros
    0.37
     Bergamo
    0.37
     Steck
    0.37
    melting
    0.37
    Activations Density 0.000%

    No Known Activations