© 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. 152924
    Prev
    Next
    INDEX
    Explanations

    file extensions

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

    checking evenness

    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
    后台
    0.46
    विड
    0.45
    ượng
    0.45
    camera
    0.44
     dagegen
    0.44
    गुज
    0.44
    Đối
    0.43
    霁
    0.43
    িদ্ধ
    0.43
    Trailer
    0.43
    POSITIVE LOGITS
     otherworldly
    0.46
     TIMES
    0.43
     Barcel
    0.43
     gubernatorial
    0.43
     condensers
    0.43
     substant
    0.42
     Wisconsin
    0.42
    はその
    0.42
     DME
    0.42
     নয়া
    0.42
    Activations Density 0.002%

    No Known Activations