© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71902
    Prev
    Next
    INDEX
    Explanations

    key-value pairs

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

    The neuron activates on numeric literals containing decimal points (floating-point numbers) in code or markup.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     it
    -1.75
    ?”
    -1.68
     ?",
    -1.64
     for
    -1.59
    😺
    -1.48
    😗
    -1.48
     сили
    -1.47
    😼
    -1.47
    ——”
    -1.46
    😸
    -1.43
    POSITIVE LOGITS
    0
    2.05
    7
    1.90
    4
    1.89
    就像是
    1.74
    6
    1.73
     estos
    1.71
    8
    1.71
    ="
    1.62
     ТАК
    1.61
     YOUR
    1.57
    Activations Density 0.002%

    No Known Activations