© 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. 118124
    Prev
    Next
    INDEX
    Explanations

    statistical or specific proper nouns

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

    research and algorithms

    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
    ↵
    0.52
     AP
    0.50
     defrost
    0.48
     avait
    0.45
    رات
    0.45
     Au
    0.44
     A
    0.43
     AU
    0.43
     amps
    0.43
     diffé
    0.42
    POSITIVE LOGITS
    гал
    0.61
    ionat
    0.54
     страну
    0.50
    pegno
    0.50
     камер
    0.48
    ionato
    0.48
     jurídico
    0.48
     стране
    0.47
    gorod
    0.47
     закона
    0.46
    Activations Density 0.000%

    No Known Activations