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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59595
    Prev
    Next
    INDEX
    Explanations

    most common

    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
     Россия
    -0.91
    AYER
    -0.89
    тные
    -0.88
    ctrica
    -0.87
    𝐑
    -0.85
     Indon
    -0.85
     přep
    -0.85
    喪
    -0.84
    外し
    -0.83
     Elek
    -0.82
    POSITIVE LOGITS
     akin
    0.89
     Hot
    0.81
    ee
    0.76
    edx
    0.73
    inthians
    0.72
    octo
    0.71
    ':
    0.71
    hof
    0.71
    hot
    0.70
     ee
    0.69
    Activations Density 0.003%

    No Known Activations