© 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. 66023
    Prev
    Next
    INDEX
    Explanations

    at all, whatsoever, indeed, flat

    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
    逐渐
    -1.70
    にぎり
    -1.70
    趼
    -1.70
    狆
    -1.70
    Инг
    -1.69
    Fakta
    -1.65
    Кита
    -1.63
     rouges
    -1.59
    Leírás
    -1.59
    maske
    -1.57
    POSITIVE LOGITS
     normalerweise
    1.93
     gewöhnlich
    1.83
    американ
    1.76
     verschied
    1.74
     Bedürfn
    1.71
     wohin
    1.71
     zufried
    1.70
     that
    1.69
     Kindern
    1.66
    躰
    1.66
    Activations Density 0.003%

    No Known Activations