© 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. 22841
    Prev
    Next
    INDEX
    Explanations

    interlocking, interlaced, intertwined

    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
    ꒥
    -1.89
    ⎔
    -1.87
    ꔹ
    -1.83
    蛲
    -1.83
    羸
    -1.80
    柽
    -1.80
    
    -1.79
     judge
    -1.79
    閦
    -1.77
    
    -1.74
    POSITIVE LOGITS
     pittore
    2.16
     leaſt
    1.98
    //
    1.98
    .,"
    1.89
    s
    1.85
    .”
    1.84
    llavero
    1.81
     ().
    1.81
     صفحۀ
    1.79
    DJANGO
    1.76
    Activations Density 0.009%

    No Known Activations