© 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. 185053
    Prev
    Next
    INDEX
    Explanations

    information after guide

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

    programming code and diverse languages

    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
     '"
    0.57
     typeface
    0.54
     刺繍
    0.54
     frequ
    0.54
     frequency
    0.50
     '
    0.50
     rhetoric
    0.49
     "\"
    0.49
     visitation
    0.49
     '-
    0.48
    POSITIVE LOGITS
    ى
    0.50
    يو
    0.48
    الم
    0.46
    ගත
    0.45
    राम
    0.45
    рю
    0.45
    लिये
    0.44
    יו
    0.44
    रम
    0.44
    কো
    0.44
    Activations Density 0.001%

    No Known Activations