© 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. 90778
    Prev
    Next
    INDEX
    Explanations

    categories, types, alternatives

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

    common industrial topics

    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
    І
    0.53
    fix
    0.52
    駐車
    0.51
    к
    0.50
    次の
    0.49
     برای
    0.48
    시
    0.48
     जिल्हा
    0.47
    ΟΥ
    0.47
    絢
    0.47
    POSITIVE LOGITS
     genomics
    0.52
     Patents
    0.50
     Genomics
    0.50
     Controllers
    0.48
     Presidents
    0.46
     Researchers
    0.46
     गेम्स
    0.45
     Founders
    0.45
     Electrochemical
    0.44
     Equals
    0.44
    Activations Density 0.000%

    No Known Activations