© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12036
    Prev
    Next
    INDEX
    Explanations

    squaring and squares

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

    The neuron activates on numeric tokens (especially measurement values or floating‐point numbers) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Durchschnitt
    0.56
    oader
    0.55
    モバイル
    0.55
    KURZBESCHREIBUNG
    0.54
     trivalent
    0.54
    uksi
    0.51
    帯
    0.51
    Meas
    0.51
    有机
    0.50
    썰
    0.50
    POSITIVE LOGITS
     squares
    1.05
     squared
    1.05
     squaring
    0.98
    squares
    0.97
    Squares
    0.97
     Squares
    0.97
     square
    0.92
    squared
    0.89
     Squared
    0.88
     Square
    0.86
    Activations Density 0.049%

    No Known Activations