© 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. 226833
    Prev
    Next
    INDEX
    Explanations

    administrative employees, Heater Guys, authorize Nadler, his bed

    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
     obtus
    0.54
    കൊ
    0.47
    OutSize
    0.46
    gic
    0.46
    
    0.44
    лізації
    0.44
    يارات
    0.44
     inteiro
    0.43
    אַר
    0.43
    തീ
    0.43
    POSITIVE LOGITS
    रीत
    0.45
     తన
    0.44
    worked
    0.44
    activ
    0.42
    ilyn
    0.42
    climate
    0.42
    issantes
    0.42
     ر
    0.41
    pattern
    0.41
     mild
    0.41
    Activations Density 0.001%

    No Known Activations