© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 2227
    Prev
    Next
    INDEX
    Explanations

    user with the results

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

    This neuron is sensitive to numeric expressions, measurements, and statistical or quantitative information.

    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
     一
    0.75
     ル
    0.73
    td
    0.72
     ท
    0.72
     水
    0.72
     生
    0.72
     半
    0.71
    T
    0.71
     特
    0.71
    bk
    0.71
    POSITIVE LOGITS
     same
    0.81
     remainder
    0.77
     perpetrators
    0.76
     perpetrator
    0.76
     proverbial
    0.73
     slightest
    0.73
     gleichen
    0.73
     appropriateness
    0.73
     gleiche
    0.73
     broadest
    0.72
    Activations Density 0.944%

    No Known Activations