© 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. 185726
    Prev
    Next
    INDEX
    Explanations

    locations and attributes

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

    conditional rendering, students, stage, process

    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
    Not in Any Lists

    No Comments

    Negative Logits
     المه
    0.53
    t
    0.50
    speed
    0.47
    les
    0.47
    is
    0.46
    m
    0.46
     mismos
    0.44
    v
    0.43
    y
    0.43
    tissue
    0.42
    POSITIVE LOGITS
     інших
    0.54
     одежды
    0.53
    静态
    0.52
     dolayı
    0.52
    manı
    0.52
    графі
    0.51
    acją
    0.51
    钀
    0.51
    䢔
    0.50
    etik
    0.50
    Activations Density 0.001%

    No Known Activations