© 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. 141445
    Prev
    Next
    INDEX
    Explanations

    special words after identifiers

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

    describing specific entities or concepts

    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
    錡
    0.48
    助手
    0.46
    بير
    0.46
    اکہ
    0.45
    materials
    0.45
    وت
    0.45
    蠔
    0.45
    ย
    0.43
    珐
    0.42
    وٹ
    0.42
    POSITIVE LOGITS
     Gölü
    0.63
     Eminem
    0.55
     Göl
    0.53
     Expanding
    0.53
     оригина
    0.52
     гром
    0.52
     Ам
    0.51
     Econom
    0.51
     Expend
    0.50
     Ando
    0.50
    Activations Density 0.000%

    No Known Activations