© 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. 10-GEMMASCOPE-RES-131K
    7. 130370
    Prev
    Next
    INDEX
    Explanations

    Angular code fragments

    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
    pecabe
    -2.11
    懨
    -2.00
    hingga
    -1.92
     小学校
    -1.87
     понял
    -1.87
    
    -1.81
     dunklen
    -1.79
    ズニー
    -1.77
    或者
    -1.75
     berühmten
    -1.75
    POSITIVE LOGITS
    /
    2.05
    (
    2.03
     '
    1.98
     &
    1.92
    —
    1.81
     /
    1.79
    `
    1.61
     (
    1.59
    ?"
    1.59
    IZ
    1.57
    Activations Density 0.016%

    No Known Activations