© 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. 72248
    Prev
    Next
    INDEX
    Explanations

    true boolean values

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on boolean‐literal tokens (e.g. “True,” “False,” “true,” “false”), i.e. it detects occurrences of true/false values.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    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
     recib
    -1.63
     asust
    -1.60
     emple
    -1.55
    苙
    -1.50
     récemment
    -1.49
     einem
    -1.48
     ?
    -1.48
     necesit
    -1.47
     drei
    -1.45
     sieben
    -1.44
    POSITIVE LOGITS
    瓩
    2.17
     climático
    1.66
    libft
    1.66
     Tatsache
    1.63
     this
    1.55
     Técnica
    1.55
     Zuhause
    1.54
     that
    1.53
    jestel
    1.52
    
    1.52
    Activations Density 0.039%

    No Known Activations