© 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. 61282
    Prev
    Next
    INDEX
    Explanations

    describing physical characteristics

    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
    了一個
    -1.59
    笵
    -1.54
    砗
    -1.40
    ísimas
    -1.38
    ViewChild
    -1.38
    thole
    -1.38
    遊んで
    -1.38
    鳎
    -1.38
    螅
    -1.38
     zostać
    -1.35
    POSITIVE LOGITS
     Often
    1.73
     Sometimes
    1.66
     Usually
    1.59
     from
    1.58
    Usually
    1.55
    Often
    1.49
     Generally
    1.45
     but
    1.45
     There
    1.34
     Although
    1.32
    Activations Density 0.201%

    No Known Activations