© 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. 86925
    Prev
    Next
    INDEX
    Explanations

    document preview

    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
     and
    -2.47
     Mereka
    -1.52
    므
    -1.35
     "."
    -1.34
     "/";
    -1.30
     ajudar
    -1.30
    を通して
    -1.30
     sentiers
    -1.30
     começar
    -1.29
     Gemeinsame
    -1.28
    POSITIVE LOGITS
    colgante
    1.88
    ing
    1.85
    で
    1.59
     açıklama
    1.58
     ۳
    1.55
     anderes
    1.55
     ۱۴
    1.52
     year
    1.52
     new
    1.52
     grinning
    1.51
    Activations Density 0.000%

    No Known Activations