© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9135
    Prev
    Next
    INDEX
    Explanations

    comparison or degree

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

    The neuron selectively fires on numeric tokens—especially measurements, counts, percentages, or other raw 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_24_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
    ávy
    0.32
    잌
    0.31
    📐
    0.30
    ską
    0.30
     getY
    0.30
    ędzy
    0.30
    さは
    0.30
     finir
    0.29
    藹
    0.29
    ség
    0.29
    POSITIVE LOGITS
     sufficiently
    0.33
    中使用
    0.31
    .
    0.30
     sogen
    0.30
     definitivo
    0.29
     sogenannten
    0.29
     предусмотре
    0.29
     suficientemente
    0.28
     sogenannte
    0.27
     definitiva
    0.27
    Activations Density 0.000%

    No Known Activations