© 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. 34-GEMMASCOPE-RES-131K
    7. 82716
    Prev
    Next
    INDEX
    Explanations

    hierarchical list, beta sheet, results

    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
     exogenous
    -0.76
     دارم
    -0.71
    ględ
    -0.71
    pektor
    -0.71
    тились
    -0.71
    typename
    -0.71
    cdonald
    -0.70
     Colección
    -0.69
    Thinking
    -0.69
     Worker
    -0.67
    POSITIVE LOGITS
     służ
    0.66
    負け
    0.64
     комп
    0.63
    Inclu
    0.62
    surf
    0.61
     Yun
    0.60
     Surf
    0.59
    夺
    0.59
     Kush
    0.59
    ַי
    0.58
    Activations Density 0.097%

    No Known Activations