© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109352
    Prev
    Next
    INDEX
    Explanations

    code and c++ includes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ët
    -0.69
     Albe
    -0.68
     Պ
    -0.67
    活着
    -0.65
    ingos
    -0.64
    Jong
    -0.64
     bashing
    -0.63
    ibr
    -0.61
     riun
    -0.61
     Mito
    -0.61
    POSITIVE LOGITS
    jap
    0.86
     insular
    0.72
     Brodie
    0.71
     inflict
    0.68
     intro
    0.67
    insular
    0.66
     intercepted
    0.66
    Ƨ
    0.66
    chenken
    0.66
    fferty
    0.65
    Activations Density 0.075%

    No Known Activations