© 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. 22-GEMMASCOPE-RES-131K
    7. 98385
    Prev
    Next
    INDEX
    Explanations

    closing punctuation; code fragment

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

    The neuron is highly responsive to semicolon tokens (i.e. statement terminators) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     by
    -1.98
     just
    -1.62
     Automó
    -1.55
    -1.48
     with
    -1.45
     devez
    -1.39
     how
    -1.33
     in
    -1.32
    ✨:
    -1.31
     has
    -1.30
    POSITIVE LOGITS
    Continu
    1.34
     horrid
    1.34
    université
    1.33
    Estab
    1.31
     dieselben
    1.31
    Зміст
    1.30
    ㌧
    1.28
    Torna
    1.27
    Mysterious
    1.27
     ____________
    1.26
    Activations Density 0.010%
    No Known Activations