© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119823
    Prev
    Next
    INDEX
    Explanations

    writing or writing about

    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
     fabricación
    -1.26
    ALLENGE
    -1.26
     encantan
    -1.25
     hura
    -1.23
    lemek
    -1.23
    诟
    -1.23
     товара
    -1.22
     vengo
    -1.21
    BATTLE
    -1.20
    apa
    -1.16
    POSITIVE LOGITS
     to
    2.66
    inverno
    1.60
     willkommen
    1.46
     Jedes
    1.39
     Definitely
    1.38
     Certainly
    1.38
     for
    1.38
    +}\
    1.38
     />);
    1.35
    СЕ
    1.34
    Activations Density 0.037%

    No Known Activations