© 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. 211845
    Prev
    Next
    INDEX
    Explanations

    specific foreign words and phrases

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

    specific tasks

    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
    abr
    0.52
    UW
    0.50
     powers
    0.49
    PL
    0.49
    Bah
    0.48
    د
    0.48
    al
    0.47
    াট
    0.47
    ABA
    0.46
    As
    0.46
    POSITIVE LOGITS
     Bolog
    0.60
     kaleidoscope
    0.58
     carne
    0.57
     flamenco
    0.57
     foie
    0.54
     fantástico
    0.53
     grotesque
    0.52
    vertrag
    0.52
     foal
    0.52
     аксессу
    0.52
    Activations Density 0.000%

    No Known Activations