© 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. 68474
    Prev
    Next
    INDEX
    Explanations

    distributed or interspersed

    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
     With
    -2.00
    With
    -1.85
    By
    -1.69
     Would
    -1.67
    iencies
    -1.66
     Anyone
    -1.63
    You
    -1.57
    .
    -1.57
    U
    -1.53
     Previously
    -1.52
    POSITIVE LOGITS
     („
    2.22
    躂
    2.05
     jezt
    1.97
    کارت
    1.94
    
    1.91
    pulseira
    1.82
     costumbres
    1.80
     queijo
    1.80
    llavero
    1.79
    皛
    1.78
    Activations Density 0.015%

    No Known Activations