© 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. 76165
    Prev
    Next
    INDEX
    Explanations

    German words for play

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

    MinMaxScaler, quantization, clipping

    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
    ต
    0.51
    t
    0.47
    следование
    0.44
    тэ
    0.43
    城乡
    0.43
     दीन
    0.43
     unrest
    0.42
     Confucian
    0.41
    守
    0.41
    laid
    0.41
    POSITIVE LOGITS
    piele
    0.53
     incentivize
    0.48
    reqParams
    0.48
     يل
    0.47
     Spielen
    0.46
    staaten
    0.46
    ارى
    0.46
    ziele
    0.46
    spiele
    0.45
     werkt
    0.45
    Activations Density 0.001%

    No Known Activations