© 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. 72942
    Prev
    Next
    INDEX
    Explanations

    website domain names

    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
     tänka
    -1.35
     läsa
    -1.30
     leyendo
    -1.30
     따라
    -1.30
     contratación
    -1.29
    name
    -1.27
    Răspunde
    -1.25
    разуме
    -1.25
     känna
    -1.25
    new
    -1.23
    POSITIVE LOGITS
     or
    2.42
     it
    2.25
     if
    1.61
     כדי
    1.48
    蟊
    1.45
     یا
    1.41
    🤞
    1.40
    1.38
    เพื่อ
    1.37
    ʏ
    1.36
    Activations Density 0.084%

    No Known Activations