© 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. 7824
    Prev
    Next
    INDEX
    Explanations

    cosmos and time

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

    The neuron fires on the Python “def” keyword, i.e. it detects the start of a function definition.

    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
    deren
    -0.90
    AGEM
    -0.82
     Psalm
    -0.81
    ㄉ
    -0.78
     EXPRESS
    -0.78
     رؤية
    -0.77
    除了
    -0.77
    𝓹
    -0.76
     famili
    -0.76
    Glej
    -0.76
    POSITIVE LOGITS
    骠
    0.94
    kiyor
    0.88
    universe
    0.84
     cosmos
    0.79
    曄
    0.77
    骆
    0.75
     Cosmos
    0.75
    LAUGHTER
    0.75
    jną
    0.75
    ált
    0.74
    Activations Density 0.000%

    No Known Activations