© 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. 129842
    Prev
    Next
    INDEX
    Explanations

    award City Texas

    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
    
    -2.22
    㐂
    -2.00
     are
    -2.00
    寕
    -1.98
    尛
    -1.98
     tries
    -1.91
    </h2>
    -1.84
    ጄ
    -1.84
    拶
    -1.80
    钲
    -1.78
    POSITIVE LOGITS
     нескольких
    2.16
    *
    2.13
     ‘‘
    2.11
    缡
    1.96
    ly
    1.95
     ‘’
    1.94
    I
    1.94
     “
    1.91
    [
    1.88
    
    1.87
    Activations Density 0.018%

    No Known Activations