© 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. 49425
    Prev
    Next
    INDEX
    Explanations

    CSS properties and values

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

    The main thing this neuron does is detect numeric literals (digits and 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_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
     кое
    -0.93
     transitioning
    -0.93
    oneofs
    -0.81
    íu
    -0.78
     millennials
    -0.78
     élastique
    -0.78
    CodeDom
    -0.77
     box
    -0.77
    FUNCTIONS
    -0.77
    instancetype
    -0.75
    POSITIVE LOGITS
    expression
    0.91
     Armada
    0.83
    pozy
    0.82
    joyed
    0.79
    пкой
    0.77
    phile
    0.77
     Wordle
    0.77
     kazak
    0.76
    urant
    0.75
    rogen
    0.74
    Activations Density 0.071%

    No Known Activations