© 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. 10-GEMMASCOPE-RES-131K
    7. 9504
    Prev
    Next
    INDEX
    Explanations

    percentages and numbers

    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_10/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
     fuese
    -2.09
     nové
    -2.06
     sentarse
    -1.91
     Acerca
    -1.85
    degna
    -1.84
    ruecos
    -1.83
    部は
    -1.83
    GEBUR
    -1.81
     fué
    -1.80
    нование
    -1.80
    POSITIVE LOGITS
     of
    2.19
     that
    2.05
     achieving
    1.80
     those
    1.77
     expertly
    1.75
     numerous
    1.70
     attaining
    1.64
    X
    1.64
     while
    1.59
    ～　
    1.59
    Activations Density 0.042%

    No Known Activations