© 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. 65029
    Prev
    Next
    INDEX
    Explanations

    words beginning with Nar

    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
     моя
    -3.08
    鯪
    -2.75
    心中的
    -2.67
     للاس
    -2.64
    CurtirCurtir
    -2.64
    髕
    -2.63
    ración
    -2.56
    ers
    -2.56
    帳に追加
    -2.56
     його
    -2.55
    POSITIVE LOGITS
     landmark
    2.55
     意思
    2.48
     That
    2.48
     brainstorm
    2.31
     realizando
    2.22
     zwart
    2.22
     extant
    2.20
    咆
    2.20
     rundown
    2.17
     powerhouse
    2.14
    Activations Density 0.003%

    No Known Activations