© 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. 45442
    Prev
    Next
    INDEX
    Explanations

    being followed by ordinals

    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
    Not in Any Lists

    No Comments

    Negative Logits
    )();
    -1.91
     was
    -1.74
     posso
    -1.63
    ?')
    -1.59
    
    -1.57
     previo
    -1.54
    ?",
    -1.52
    ()=>{
    -1.51
    😮
    -1.51
     worden
    -1.50
    POSITIVE LOGITS
     ด้วย
    1.96
     It
    1.85
     klassischen
    1.72
     Каждый
    1.67
     Gespräche
    1.60
     wiederholt
    1.59
    Donde
    1.59
     naszego
    1.58
    睒
    1.57
     careful
    1.55
    Activations Density 0.010%

    No Known Activations