© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 5081
    Prev
    Next
    INDEX
    Explanations

    px;

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

    The neuron activates on numeric measurement tokens—especially width×height or dpi-style dimension figures in markup or image metadata.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    臨界
    0.54
    అ
    0.49
    अपनी
    0.48
    కరణ
    0.48
    ಿಗೆ
    0.48
     Pixel
    0.46
    relativePath
    0.46
     प्रतिशत
    0.46
    Pixel
    0.46
     porcent
    0.45
    POSITIVE LOGITS
     schwarz
    0.55
    aneers
    0.50
    }^{\#
    0.47
    ей
    0.46
    êts
    0.46
    يره
    0.46
    (!)
    0.44
    irds
    0.44
     coloured
    0.44
     (!
    0.44
    Activations Density 0.000%

    No Known Activations