© 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. 34-GEMMASCOPE-RES-131K
    7. 47137
    Prev
    Next
    INDEX
    Explanations

    variable or property declarations

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

    The neuron fires on numeric literal tokens in code (i.e. numbers).

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    　↓
    -1.48
    Zubereitung
    -1.34
     PÅ
    -1.33
    久し
    -1.29
    zbęd
    -1.29
    Struktur
    -1.28
     Chapitre
    -1.27
    Menge
    -1.25
     ciment
    -1.24
    Rozmiar
    -1.24
    POSITIVE LOGITS
    int
    1.86
     int
    1.85
     String
    1.55
     bool
    1.54
     boolean
    1.42
    bool
    1.41
     double
    1.36
     float
    1.34
    double
    1.30
     Date
    1.28
    Activations Density 0.019%

    No Known Activations