© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114200
    Prev
    Next
    INDEX
    Explanations

    worthy and unworthy

    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
    Negative Logits
    鲼
    -3.14
    utriche
    -3.09
    usschuss
    -2.72
    änemark
    -2.59
    writerow
    -2.55
    𓁹
    -2.55
    鴆
    -2.55
    wortet
    -2.50
    gencias
    -2.50
    屛
    -2.44
    POSITIVE LOGITS
    0
    3.61
     
    3.17
    While
    2.91
    Although
    2.58
    "
    2.50
    
    2.47
    事も
    2.45
    Without
    2.44
    ,’
    2.41
     Their
    2.39
    Activations Density 0.002%

    No Known Activations