© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 26090
    Prev
    Next
    INDEX
    Explanations

    web applications and automation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     тә
    0.38
    ✧
    0.37
     Tup
    0.37
     Mac
    0.37
     (†
    0.36
    optera
    0.36
    TCP
    0.36
     ont
    0.35
    ン
    0.35
     sprawy
    0.35
    POSITIVE LOGITS
    emie
    0.44
     মুল
    0.39
    িক্ত
    0.39
    ুনিক
    0.39
    heroku
    0.38
    ỗ
    0.38
     enige
    0.38
    のある
    0.37
    seller
    0.37
    િંગ
    0.37
    Activations Density 0.000%

    No Known Activations