© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72493
    Prev
    Next
    INDEX
    Explanations

    pronoun gets something

    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
     colorido
    -2.08
     zapato
    -1.98
    {
    -1.98
     dubbel
    -1.94
    性价比
    -1.94
     mavi
    -1.93
     gancho
    -1.91
     estampado
    -1.91
    𓋼
    -1.84
    hasilkan
    -1.84
    POSITIVE LOGITS
     ‘
    2.19
     to
    2.02
    ’)
    1.98
     eer
    1.94
     faked
    1.93
     Moreover
    1.92
     rid
    1.91
    
    1.88
     ‘‘
    1.86
     ‘’
    1.85
    Activations Density 0.013%

    No Known Activations