© 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. 22-GEMMASCOPE-RES-131K
    7. 16437
    Prev
    Next
    INDEX
    Explanations

    Use of this source code

    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_22/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
    ⾞
    -1.91
    蚰
    -1.84
    
    -1.82
    ternut
    -1.80
    still
    -1.74
    櫺
    -1.71
    terscotch
    -1.70
     hombro
    -1.67
    厖
    -1.67
    romeda
    -1.64
    POSITIVE LOGITS
     of
    2.05
     to
    1.57
     in
    1.48
     özel
    1.47
     only
    1.45
    簾
    1.43
     только
    1.41
    %)
    1.41
     uber
    1.37
     methods
    1.35
    Activations Density 0.034%

    No Known Activations