© 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. 98236
    Prev
    Next
    INDEX
    Explanations

    code structure elements

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

    The neuron fires on semicolon tokens that terminate statements or block declarations across various programming languages.

    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
     Lainnya
    -1.10
    越來
    -1.04
     інших
    -1.00
     other
    -0.96
     Consumo
    -0.93
     Kto
    -0.92
     others
    -0.90
    祈り
    -0.89
    組織
    -0.89
     Wartawan
    -0.86
    POSITIVE LOGITS
     ſte
    1.04
    zepte
    1.01
    ÍST
    1.01
    lück
    1.00
    BOTH
    0.99
    ੲ
    0.99
    "}>
    0.96
    devamını
    0.95
     …”
    0.94
    ("")
    0.94
    Activations Density 0.005%

    No Known Activations