© 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. 34-GEMMASCOPE-RES-131K
    4. 90688
    Prev
    Next
    INDEX
    Explanations

    proper nouns and 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_34/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
    상
    -0.81
     روی
    -0.79
     Entrepreneur
    -0.77
     curated
    -0.76
     ورز
    -0.76
     Comercial
    -0.76
    温和
    -0.76
    nė
    -0.75
     segn
    -0.75
    Ӧ
    -0.75
    POSITIVE LOGITS
    ホルモン
    0.82
    vård
    0.81
    Sedangkan
    0.80
     esferas
    0.77
     Septiembre
    0.76
    Misión
    0.75
    omiya
    0.75
     koos
    0.75
    唠
    0.74
     labai
    0.73
    Activations Density 0.003%

    No Known Activations