© 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. 166602
    Prev
    Next
    INDEX
    Explanations

    easy, uploads, sharing, questions

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

    provided, avoid

    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
     OFF
    0.48
     wygod
    0.48
    检查
    0.46
    '
    0.46
    Off
    0.46
     an
    0.45
    Score
    0.44
    记
    0.44
    Rent
    0.44
    る
    0.44
    POSITIVE LOGITS
     प्रणाली
    0.46
    istern
    0.46
     Huerta
    0.46
    óch
    0.45
     कॉम
    0.45
    梅里
    0.45
    komen
    0.45
     raat
    0.44
    kaa
    0.44
    äischen
    0.44
    Activations Density 0.001%

    No Known Activations