© 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. 38425
    Prev
    Next
    INDEX
    Explanations

    maximum limits and settings

    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
     incorpora
    -2.42
     accedi
    -2.41
     brevemente
    -2.34
    🛇
    -2.33
     firmado
    -2.33
     anuncia
    -2.31
    vape
    -2.30
    
    -2.30
    wiches
    -2.28
    thail
    -2.28
    POSITIVE LOGITS
    4
    3.02
    5
    2.77
    s
    2.75
    In
    2.64
    3
    2.63
    7
    2.50
    Two
    2.45
    蛧
    2.44
    ities
    2.36
    1
    2.33
    Activations Density 0.012%

    No Known Activations