© 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. 129917
    Prev
    Next
    INDEX
    Explanations

    closing quotation marks

    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
     has
    -1.87
    While
    -1.66
    Since
    -1.57
     this
    -1.56
    There
    -1.55
     are
    -1.55
     и
    -1.55
    Because
    -1.53
     seems
    -1.49
     și
    -1.48
    POSITIVE LOGITS
    ";
    1.57
    撄
    1.52
    ໊
    1.52
     kinderen
    1.50
     Duitsland
    1.47
    Indonesia
    1.46
    岨
    1.45
    𓆸
    1.44
     Amerikaanse
    1.44
     несколь
    1.39
    Activations Density 0.018%

    No Known Activations