© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 130251
    Prev
    Next
    INDEX
    Explanations

    The neuron specializes in spotting statement-terminating semicolons in source code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    import or code structure

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    --
    -1.02
     Jahrgang
    -0.93
     konsumsi
    -0.88
     姜
    -0.88
    nowa
    -0.88
    cgi
    -0.88
    věr
    -0.86
    酒
    -0.85
    kých
    -0.85
    nowy
    -0.85
    POSITIVE LOGITS
    معلومات
    0.94
    möglichen
    0.91
    纛
    0.86
     лето
    0.86
     oficiales
    0.84
     estimates
    0.84
    らしいです
    0.84
     Update
    0.84
     derived
    0.83
     respetar
    0.83
    Activations Density 0.015%

    No Known Activations