© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86509
    Prev
    Next
    INDEX
    Explanations

    LA followed by punctuation or word

    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
    亙
    -2.75
    鄖
    -2.73
    不会
    -2.73
     學
    -2.66
     If
    -2.61
     bekannte
    -2.59
    pecabe
    -2.56
     飯店
    -2.52
    是
    -2.47
    采用
    -2.36
    POSITIVE LOGITS
    e
    2.53
     votre
    2.52
     notre
    2.50
    افی
    2.48
    缡
    2.45
     aussi
    2.44
     vraiment
    2.34
    焔
    2.33
    ти
    2.30
     нашу
    2.27
    Activations Density 0.004%

    No Known Activations