© 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. 71087
    Prev
    Next
    INDEX
    Explanations

    areas

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

    areas for improvement

    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
     to
    0.89
     milj
    0.84
    ث
    0.82
    st
    0.80
    ר
    0.77
    ૧
    0.77
    ၅
    0.76
    ر
    0.75
    )،
    0.73
     ballots
    0.73
    POSITIVE LOGITS
    areas
    1.17
    Areas
    1.09
     areas
    1.06
     områ
    1.05
     áreas
    1.03
    Area
    0.99
     området
    0.99
     oblasti
    0.98
    områ
    0.97
     области
    0.96
    Activations Density 0.241%

    No Known Activations