© 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. 22715
    Prev
    Next
    INDEX
    Explanations

    introducing factual information

    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
     We
    -2.94
    
    -2.31
     –
    -2.31
     was
    -2.30
    ."
    -2.25
    (
    -2.25
                    
    -2.20
    ="
    -2.17
     mélang
    -2.11
    ',
    -2.08
    POSITIVE LOGITS
    er
    2.83
     facts
    2.73
    鮃
    2.72
    ſu
    2.41
    出来た
    2.41
    ᝢ
    2.36
    ၟ
    2.28
    逕
    2.25
    ﱠ
    2.25
     reputation
    2.22
    Activations Density 0.003%

    No Known Activations