© 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. 85304
    Prev
    Next
    INDEX
    Explanations

    permit and acquisition

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

    party planning, duplicate requests, or ID identification

    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
    Negative Logits
    有点
    0.53
    bm
    0.46
    您
    0.45
     Liner
    0.45
    Low
    0.44
    マー
    0.44
    പ്പെ
    0.44
    执行
    0.44
    ยู
    0.44
    选
    0.43
    POSITIVE LOGITS
     considerar
    0.47
     партия
    0.47
     пациен
    0.46
     時
    0.46
     sanciones
    0.45
     läng
    0.45
     дисципли
    0.44
     ""`
    0.44
     voorz
    0.44
     alarg
    0.43
    Activations Density 0.000%

    No Known Activations