© 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. 11226
    Prev
    Next
    INDEX
    Explanations

    paths from all

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

    The neuron activates on numeric expressions—numbers, measurements, coordinates, and other digit‐based tokens.

    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
     verticales
    0.69
     вертика
    0.66
    ┳
    0.62
     Whitehall
    0.61
     rectangular
    0.60
    ylinder
    0.60
     recto
    0.59
     dikdört
    0.58
    Vertical
    0.58
     dimensiones
    0.57
    POSITIVE LOGITS
     النقطه
    0.76
    点
    0.74
    點
    0.70
     circum
    0.69
    Point
    0.68
    점이
    0.66
     จุด
    0.66
     Point
    0.65
     点
    0.65
    線
    0.65
    Activations Density 0.043%

    No Known Activations