© 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. 20374
    Prev
    Next
    INDEX
    Explanations

    meta or metadata in structured data

    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
    </i>
    -1.75
     to
    -1.61
     who
    -1.57
     gelesen
    -1.52
    都知道
    -1.48
    我都
    -1.45
    ="'
    -1.41
     inyección
    -1.41
    tanian
    -1.41
    "];
    -1.41
    POSITIVE LOGITS
     abiye
    1.88
     diki
    1.80
     etek
    1.79
     şal
    1.73
    _
    1.73
    深渊
    1.70
     ilg
    1.69
     çi
    1.63
    álise
    1.63
     araba
    1.63
    Activations Density 0.021%

    No Known Activations