© 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. 75705
    Prev
    Next
    INDEX
    Explanations

    flight, modules, women, reasons

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

    quadratic equations and researchers

    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
    ೆಂದು
    0.57
     ______
    0.44
     dedicata
    0.43
     amminist
    0.43
     tutto
    0.42
     festa
    0.42
     gobier
    0.41
     früher
    0.41
     _______
    0.41
     controla
    0.41
    POSITIVE LOGITS
    วี
    0.46
    Linkedin
    0.46
    Radial
    0.44
    Geo
    0.44
    书籍
    0.43
    ｉ
    0.43
    Wayne
    0.42
    ழி
    0.42
    Servlet
    0.42
    Sexual
    0.41
    Activations Density 0.000%

    No Known Activations