© 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. 146752
    Prev
    Next
    INDEX
    Explanations

    guarantee, trauma, uniqueness, franchise

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

    unique not null sql

    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
    milk
    0.52
    her
    0.49
    rans
    0.48
    ep
    0.47
    empty
    0.47
    n
    0.46
    ren
    0.46
    aligned
    0.46
    through
    0.45
    1
    0.45
    POSITIVE LOGITS
    នៅលើ
    0.48
    Batter
    0.47
     dạng
    0.44
     oraș
    0.44
    Acces
    0.44
     senator
    0.44
     кеңсе
    0.44
     ASSEM
    0.44
     кеңсеси
    0.43
     média
    0.43
    Activations Density 0.000%

    No Known Activations