© 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. 34-GEMMASCOPE-RES-131K
    7. 38311
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

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

    The neuron is triggered by mentions of the period (“dot”) character (e.g. “middle dot,” splitting on a dot) in code or text.

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

    No Comments

    Negative Logits
    entliche
    -0.72
     rosemary
    -0.72
     apparently
    -0.71
     Wär
    -0.71
     einstellen
    -0.71
     initView
    -0.70
    يند
    -0.70
     ardour
    -0.70
     appuntamento
    -0.69
    platinum
    -0.68
    POSITIVE LOGITS
     Operator
    1.07
     operator
    1.02
     Jahre
    0.94
    Operator
    0.92
     symbol
    0.91
     operador
    0.88
     (§
    0.86
     Operators
    0.85
     ASCII
    0.85
    нез
    0.85
    Activations Density 0.118%

    No Known Activations