© 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. 34-GEMMASCOPE-RES-131K
    7. 65291
    Prev
    Next
    INDEX
    Explanations

    features, attributes, variables, dimensions

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

    The main thing this neuron does is detect numeric tokens and expressions (e.g. counts, dimensions, and other numbers).

    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
    žem
    -0.87
    hWnd
    -0.77
    doctrine
    -0.75
    ූ
    -0.72
     特別
    -0.71
    igroup
    -0.71
    IVersion
    -0.71
    THREE
    -0.71
     بنت
    -0.71
    ADT
    -0.69
    POSITIVE LOGITS
     features
    2.33
     feature
    2.06
     attributes
    2.03
    features
    1.89
     variables
    1.71
     attribute
    1.69
    feature
    1.69
    Features
    1.62
     Features
    1.61
    FEATURES
    1.61
    Activations Density 0.050%

    No Known Activations