© 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. 50368
    Prev
    Next
    INDEX
    Explanations

    copyright notices and header guards

    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
     Zwer
    -0.79
    ̾
    -0.78
     McEl
    -0.74
    ￦
    -0.73
    اب
    -0.73
     Chemistry
    -0.71
     Erd
    -0.71
    Mitä
    -0.69
    elsif
    -0.69
     Site
    -0.68
    POSITIVE LOGITS
     Cann
    0.66
     tỉ
    0.66
     Hr
    0.65
    Imgs
    0.63
     leisten
    0.63
    ictus
    0.63
    程度上
    0.61
    わかる
    0.60
     adoptive
    0.60
    回了
    0.60
    Activations Density 0.113%

    No Known Activations