© 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. 246694
    Prev
    Next
    INDEX
    Explanations

    December Hung

    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
    cate
    0.49
    ప్త
    0.48
    דה
    0.46
    ندا
    0.45
     розподі
    0.45
     സിപി
    0.45
    דיה
    0.43
    晎
    0.43
    фе
    0.43
     стаття
    0.42
    POSITIVE LOGITS
    ashes
    0.51
     porro
    0.50
    ’
    0.49
     Oy
    0.48
     yö
    0.45
     Dona
    0.43
     lesbian
    0.43
    মিটার
    0.43
     Croatian
    0.43
     Codex
    0.43
    Activations Density 0.000%

    No Known Activations