© 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. 114123
    Prev
    Next
    INDEX
    Explanations

    administrative or technical terms

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

    fried alongside meat

    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
     EFFECTS
    0.50
     %``
    0.46
    SED
    0.44
     AUTHOR
    0.44
    🫦
    0.43
     เห็น
    0.42
     ακό
    0.42
    ్యంలో
    0.42
    MENT
    0.41
     ****",
    0.40
    POSITIVE LOGITS
    administrat
    0.47
     Enseñanza
    0.45
    informatics
    0.45
     wifi
    0.44
     طل
    0.43
     administrat
    0.43
    اد
    0.43
     فرهنگی
    0.43
     acrob
    0.42
    డవ
    0.42
    Activations Density 0.001%

    No Known Activations