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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 41895
    Prev
    Next
    INDEX
    Explanations

    non-destructive correction

    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
     compromis
    -1.88
     accessoire
    -1.70
     paru
    -1.63
    
    -1.62
    
    -1.57
    ᨆ
    -1.56
     sembl
    -1.55
     noten
    -1.55
    嫋
    -1.54
     verbe
    -1.53
    POSITIVE LOGITS
     with
    2.13
     we
    1.84
    They
    1.79
    It
    1.78
     like
    1.70
     of
    1.66
    ),
    1.63
     all
    1.56
     We
    1.55
     there
    1.48
    Activations Density 0.018%

    No Known Activations