© 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. 127827
    Prev
    Next
    INDEX
    Explanations

    group unique versions of file

    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
    Negative Logits
     before
    -1.00
     on
    -0.98
     or
    -0.97
     with
    -0.85
     seven
    -0.81
    crops
    -0.80
     Eight
    -0.80
    ViewComponent
    -0.78
     that
    -0.78
     first
    -0.77
    POSITIVE LOGITS
    
    0.93
     interessant
    0.92
     interessante
    0.90
     fotograf
    0.89
     جمع
    0.89
    จาก
    0.88
     тогда
    0.87
    Then
    0.85
    Kw
    0.85
    ИА
    0.85
    Activations Density 0.073%

    No Known Activations