© 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. 106313
    Prev
    Next
    INDEX
    Explanations

    raise an eyebrow and say "so"

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

    time periods or games

    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
    网络的
    0.50
    某
    0.50
    كت
    0.46
    дия
    0.46
    找
    0.45
     deflected
    0.45
    曼
    0.45
    阡
    0.45
    簸
    0.44
    正则
    0.44
    POSITIVE LOGITS
     Á
    0.50
     verg
    0.47
     ainsi
    0.46
     á
    0.46
     primit
    0.46
    ጅም
    0.46
     ADR
    0.44
     im
    0.44
     Ainsi
    0.43
     gauche
    0.43
    Activations Density 0.000%

    No Known Activations