© 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. 45476
    Prev
    Next
    INDEX
    Explanations

    words starting with var

    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
    神
    -4.03
    踽
    -3.67
    呖
    -3.33
    圌
    -3.33
    驁
    -3.28
    茕
    -3.27
    
    -3.19
    䊐
    -3.19
    髕
    -3.11
    
    -3.06
    POSITIVE LOGITS
    2
    4.03
    \
    3.56
     
    3.42
    7
    3.31
    ar
    3.23
     Getting
    3.11
     Having
    3.09
     Because
    3.09
    6
    3.08
     Contrary
    3.00
    Activations Density 0.009%

    No Known Activations