© 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. 12076
    Prev
    Next
    INDEX
    Explanations

    compressive and tensile properties

    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
    hassee
    -1.50
     太陽
    -1.48
    ad
    -1.48
    群众
    -1.46
     ؛
    -1.45
    did
    -1.44
    M
    -1.41
     recentemente
    -1.38
     reali
    -1.37
     sachsen
    -1.36
    POSITIVE LOGITS
     ONLY
    1.61
    Условия
    1.47
    Особенности
    1.45
     $
    1.41
    𓋼
    1.39
     and
    1.36
    Spécifications
    1.35
    埙
    1.31
     также
    1.28
     '
    1.27
    Activations Density 0.033%

    No Known Activations