© 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. 13341
    Prev
    Next
    INDEX
    Explanations

    code segments ending in punctuation

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

    The neuron fires on camelCase method names with “Get” in them (e.g. “multiGet”).

    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
    Bigr
    -1.03
     október
    -1.02
     casar
    -1.00
    фю
    -0.98
    諳
    -0.98
     terça
    -0.97
    ㎏
    -0.97
     Schweden
    -0.96
     surla
    -0.94
    tgärder
    -0.94
    POSITIVE LOGITS
     ‘
    1.08
    -
    1.04
     mooring
    1.02
     администрации
    1.02
    ønne
    0.93
     proberen
    0.91
     batman
    0.90
     renegade
    0.90
     sàn
    0.90
    _
    0.90
    Activations Density 0.003%

    No Known Activations