© 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. 71370
    Prev
    Next
    INDEX
    Explanations

    specific dates

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

    history, city, increases, developers, plentiful, fast, frames

    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
     ግን
    0.52
     일반적으로
    0.49
    诚
    0.46
     vagin
    0.46
     belge
    0.46
     adherents
    0.46
     밤
    0.45
    NGTH
    0.45
     empezar
    0.44
     electrolysis
    0.44
    POSITIVE LOGITS
    剞
    0.42
     I
    0.40
    Active
    0.39
    சன்
    0.38
    ubi
    0.38
     Marino
    0.38
    ado
    0.38
    J
    0.38
    او
    0.37
     Siro
    0.37
    Activations Density 0.000%

    No Known Activations