© 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. 176813
    Prev
    Next
    INDEX
    Explanations

    marked up or with importance

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

    fast loading, run it, grab breakfast

    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
     Constantine
    0.51
     Константи
    0.49
    тости
    0.48
     Сте
    0.46
     Sait
    0.46
    鉋
    0.46
     Position
    0.46
     Constant
    0.46
     RBS
    0.45
     POSITION
    0.44
    POSITIVE LOGITS
    ofer
    0.48
    enf
    0.47
    BAI
    0.45
    ópez
    0.44
    िए
    0.44
    í
    0.44
    öl
    0.43
    IPA
    0.43
    MBA
    0.43
    uff
    0.42
    Activations Density 0.003%

    No Known Activations