© 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. 152692
    Prev
    Next
    INDEX
    Explanations

    with your, ship nearly, if you

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

    generally hunting

    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
    Not in Any Lists

    No Comments

    Negative Logits
    i
    0.44
     AIDS
    0.44
    保证
    0.43
     RECOMM
    0.43
    觜
    0.42
     successivement
    0.42
     Recommended
    0.41
    摊
    0.41
    前面的
    0.41
    Epid
    0.40
    POSITIVE LOGITS
     unattainable
    0.47
     diatom
    0.46
     روسیه
    0.45
     silos
    0.45
     HAY
    0.45
     '_
    0.44
    आय
    0.44
     millet
    0.44
     plataformas
    0.44
     чемпионате
    0.43
    Activations Density 0.000%

    No Known Activations