© 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. 226480
    Prev
    Next
    INDEX
    Explanations

    legal and sports terms

    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
     Гру
    0.50
     giường
    0.49
    ationen
    0.48
    ፥
    0.46
     biologically
    0.45
    ^{\
    0.45
     ఎమ్
    0.44
    FormBorderStyle
    0.44
     هيا
    0.44
    iód
    0.43
    POSITIVE LOGITS
    ssä
    0.49
     playable
    0.46
     toit
    0.46
    エ
    0.45
     mercato
    0.45
     waw
    0.45
     partie
    0.44
     contender
    0.44
     bew
    0.44
    후
    0.43
    Activations Density 0.000%

    No Known Activations