© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 45459
    Prev
    Next
    INDEX
    Explanations

    code structure and variable names

    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
    以上です
    -1.44
    Furthermore
    -1.40
    ございません
    -1.38
    Ширина
    -1.37
    並且
    -1.36
    當中
    -1.35
     entendre
    -1.33
    Далее
    -1.27
    Ой
    -1.24
     Furthermore
    -1.21
    POSITIVE LOGITS
    '){
    1.92
    {
    
    1.91
    )
    
    1.69
    ()
    
    1.67
    __('
    1.62
    )});
    1.57
    ):
    
    1.57
    ]){
    1.52
    }>;
    1.52
     objectAtIndex
    1.52
    Activations Density 0.180%

    No Known Activations