© 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. 130628
    Prev
    Next
    INDEX
    Explanations

    code structure and elements

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

    The neuron fires on code tokens that introduce or declare functions/methods (e.g. “protected void,” “function,” etc.).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     “
    -1.90
     The
    -1.80
     (“
    -1.68
     -
    -1.62
     l
    -1.59
     |
    -1.55
     it
    -1.52
     vielen
    -1.45
    方に
    -1.41
     —
    -1.41
    POSITIVE LOGITS
     westfalen
    1.85
     siena
    1.83
     venezia
    1.80
     tramont
    1.80
     oliveira
    1.78
     funghi
    1.77
     censi
    1.73
     maroc
    1.70
     perna
    1.70
     lorenzo
    1.70
    Activations Density 0.000%

    No Known Activations