© 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. 13549
    Prev
    Next
    INDEX
    Explanations

    approximations of distance or time

    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
    ementara
    -1.75
     niya
    -1.60
    
    -1.60
     zoude
    -1.60
    each
    -1.59
    リエステル
    -1.59
     would
    -1.51
    ﹔
    -1.49
     ТА
    -1.48
    vrouw
    -1.47
    POSITIVE LOGITS
    <bos>
    1.98
    .’
    1.73
     
    1.70
    ↵
    1.52
    ?
    1.42
     i
    1.39
    今では
    1.38
     längere
    1.35
    ,’
    1.35
    ’.
    1.35
    Activations Density 0.026%

    No Known Activations