© 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. 1042
    Prev
    Next
    INDEX
    Explanations

    RM price ranges

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

    The neuron is triggered by numeric measurement values—especially multi‐digit figures denoting dimensions or resolutions (e.g. “1920 × 1080,” “300 dpi,” “30 fps”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    numerical dimensions and measurements, particularly pixel dimensions and physical measurements in formats like "X x Y" or standalone numbers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    numerical measurements and dimensions, especially sizes, resolutions, and monetary amounts.

    oai_token-act-pair · gpt-5Triggered 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
     personnelles
    0.45
     établissement
    0.45
     réforme
    0.44
    govt
    0.44
    欉
    0.44
     लोका
    0.44
     क्रमांका
    0.43
     हृदया
    0.43
     guvern
    0.42
     reconnaît
    0.42
    POSITIVE LOGITS
    5
    0.77
     width
    0.72
    6
    0.72
    8
    0.71
    2
    0.68
    3
    0.64
    4
    0.63
    7
    0.63
    9
    0.63
     maxWidth
    0.62
    Activations Density 0.339%

    No Known Activations