© 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. 68488
    Prev
    Next
    INDEX
    Explanations

    software package 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
    2
    -1.78
    dération
    -1.64
    眎
    -1.58
     菇
    -1.50
    1
    -1.48
    Karakteristik
    -1.48
     tilbud
    -1.48
    ⣞
    -1.41
    耵
    -1.41
    が少ない
    -1.41
    POSITIVE LOGITS
     by
    2.19
            
    1.82
          
    1.79
    </h2>
    1.73
     как
    1.72
    ᾶ
    1.72
        
    1.63
    ми
    1.59
     aasta
    1.58
         
    1.56
    Activations Density 0.024%

    No Known Activations