© 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. 10057
    Prev
    Next
    INDEX
    Explanations

    visiting or a visit

    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
    >
    -1.85
     were
    -1.85
     pendek
    -1.77
     viande
    -1.73
    ・「
    -1.72
     veau
    -1.72
     १
    -1.68
    ically
    -1.67
    鷙
    -1.66
     sucre
    -1.65
    POSITIVE LOGITS
     puzzling
    2.47
     was
    2.44
     fleeting
    2.42
    谖
    2.25
     tangled
    2.14
     paramount
    2.02
    摃
    2.02
     harsh
    2.00
     The
    1.95
     hallmark
    1.88
    Activations Density 0.009%

    No Known Activations