© 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. 100136
    Prev
    Next
    INDEX
    Explanations

    random and its subsequent words

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

    random number and item generation

    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
    在
    0.77
     in
    0.68
     في
    0.61
    يه
    0.59
    ข
    0.53
     в
    0.52
    もら
    0.52
     தேவ
    0.52
    之为
    0.52
    도
    0.52
    POSITIVE LOGITS
    ä
    0.68
    随机
    0.63
    OL
    0.62
    as
    0.55
    ochastic
    0.53
    ８
    0.53
    ವಾಗಿ
    0.52
    EN
    0.52
    حدیث
    0.51
     brasileiro
    0.51
    Activations Density 0.046%

    No Known Activations