© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 427
    Prev
    Next
    INDEX
    Explanations

    scoreboard counts

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

    This neuron detects numeric tokens (especially numbers, including those with decimal points).

    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
    TypeOf
    0.32
     sop
    0.31
    <0x0D>
    0.30
    ят
    0.30
     Galile
    0.30
    untitled
    0.29
     concealed
    0.29
     t
    0.28
     hidden
    0.28
     gal
    0.28
    POSITIVE LOGITS
     Brendan
    0.51
     Revenues
    0.47
     Larry
    0.46
     Anthony
    0.46
     Amid
    0.45
     Hanya
    0.45
     Mike
    0.45
     Gary
    0.44
     Başkanı
    0.44
     Nathan
    0.44
    Activations Density 0.083%

    No Known Activations