© 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. 102934
    Prev
    Next
    INDEX
    Explanations

    closing punctuation

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

    The neuron responds to statement‐terminating punctuation in code—chiefly semicolons and closing curly braces.

    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
     returned
    -1.52
     returning
    -1.38
     return
    -1.38
     returns
    -1.34
    Return
    -1.33
     Return
    -1.30
    returned
    -1.28
    returning
    -1.28
     Returned
    -1.27
    返回
    -1.24
    POSITIVE LOGITS
    💶
    0.93
     Norvège
    0.85
     التش
    0.83
     rê
    0.81
    alore
    0.80
    euros
    0.78
    imab
    0.77
     ولو
    0.77
     Beecher
    0.77
    你现在
    0.77
    Activations Density 0.003%

    No Known Activations