© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36630
    Prev
    Next
    INDEX
    Explanations

    code punctuation and symbols

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

    The neuron is primarily detecting statement-terminating semicolons 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
     aquella
    -1.03
     filosó
    -0.96
    ditional
    -0.94
    tcb
    -0.84
     Turkish
    -0.84
     charity
    -0.83
    iffa
    -0.82
    onatos
    -0.82
    獗
    -0.81
     Philanth
    -0.81
    POSITIVE LOGITS
    وزش
    0.96
    impin
    0.87
    不定
    0.83
    ENSITY
    0.81
    "));
    0.79
     =
    0.78
    ginate
    0.77
    нить
    0.76
     размера
    0.75
    我们在
    0.75
    Activations Density 0.002%

    No Known Activations