© 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. 103139
    Prev
    Next
    INDEX
    Explanations

    back to or into

    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
    懨
    -2.34
    趼
    -2.27
    0
    -2.23
    𐐪
    -2.23
    Kontra
    -2.22
    Genial
    -2.17
    
    -2.16
    我们需要
    -2.16
    夤
    -2.13
    ޒ
    -2.11
    POSITIVE LOGITS
     ‘
    2.75
     rid
    2.63
     to
    2.50
    ’)
    2.06
     ‘‘
    1.99
    ’.
    1.98
     There
    1.95
     In
    1.95
    ."
    1.88
    ’,
    1.87
    Activations Density 0.003%

    No Known Activations