© 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. 10-GEMMASCOPE-RES-131K
    7. 69292
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
     is
    -2.44
     will
    -2.39
     are
    -1.80
     otros
    -1.57
     have
    -1.57
     shows
    -1.57
     czeka
    -1.52
     serdecznie
    -1.48
     appear
    -1.45
    <blockquote>
    -1.45
    POSITIVE LOGITS
    eeeeeeee
    1.84
    ,«
    1.82
    ledad
    1.80
    eeee
    1.73
    rrrrr
    1.73
    ugges
    1.72
    rrrrrr
    1.70
    eeeee
    1.70
    ogues
    1.67
     JOUR
    1.66
    Activations Density 0.152%

    No Known Activations