© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8958
    Prev
    Next
    INDEX
    Explanations

    listing items with "and"

    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
     you
    -1.80
     there
    -1.44
     \
    -1.38
    -1.38
    td
    -1.38
    ”，
    -1.34
     it
    -1.31
    t
    -1.28
    ip
    -1.27
    ts
    -1.25
    POSITIVE LOGITS
     a
    1.81
    鬭
    1.73
    Instead
    1.73
    
    1.60
    ໊
    1.55
    zapatillas
    1.54
    xvii
    1.48
    accessoires
    1.45
    ：……
    1.41
    ródło
    1.38
    Activations Density 0.119%

    No Known Activations