© 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. 85827
    Prev
    Next
    INDEX
    Explanations

    conjunctions and proper nouns

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

    bash file commands

    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
    te
    0.51
    cie
    0.49
     T
    0.49
    type
    0.47
    t
    0.46
    nd
    0.46
    פל
    0.46
    is
    0.44
    st
    0.44
     C
    0.44
    POSITIVE LOGITS
     mân
    0.63
    vì
    0.54
     respuestas
    0.52
     toddlers
    0.51
     dentées
    0.50
     économiques
    0.50
     öğren
    0.49
     öğrenc
    0.48
     ót
    0.48
     expresión
    0.48
    Activations Density 0.000%

    No Known Activations