© 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. 9581
    Prev
    Next
    INDEX
    Explanations

    enc / conc / Center

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

    The neuron is highly activated by numeric tokens—especially large numbers or multi-digit numerals—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_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
    ства
    0.60
    datasource
    0.60
     diferentes
    0.59
    np
    0.58
    拔
    0.58
    屿
    0.55
    不用
    0.54
    neu
    0.54
    kové
    0.52
    nitrogen
    0.52
    POSITIVE LOGITS
     ancillary
    0.66
    ENC
    0.61
    )/
    0.58
     ক্যার
    0.58
    inc
    0.56
     Enc
    0.56
    विटी
    0.55
    Inc
    0.55
     normally
    0.54
     anc
    0.54
    Activations Density 0.578%

    No Known Activations