© 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. 68741
    Prev
    Next
    INDEX
    Explanations

    following steps instructions

    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
     these
    -1.79
     with
    -1.55
     that
    -1.46
    Finalmente
    -1.38
     it
    -1.38
     when
    -1.30
    Each
    -1.30
    Often
    -1.30
     поэтому
    -1.29
     because
    -1.27
    POSITIVE LOGITS
     nela
    1.35
    “
    1.34
     occidentale
    1.30
     delightfully
    1.28
     ולה
    1.28
     tillsammans
    1.24
     roś
    1.21
     продаже
    1.21
    
    1.20
    ENDIX
    1.20
    Activations Density 0.080%

    No Known Activations