© 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. 13869
    Prev
    Next
    INDEX
    Explanations

    exchange method, galaxy clusters, earthquake struck

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

    This neuron is tuned to spot numeric tokens—especially decimal or statistical 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
    \">\
    0.82
    $\{
    0.82
    ETIME
    0.82
    ');
    0.81
     чыныгы
    0.81
    🧂
    0.81
     Gesund
    0.80
    শক
    0.80
     perfek
    0.80
    );
    0.79
    POSITIVE LOGITS
    et
    0.72
    but
    0.72
    ه
    0.71
    सा
    0.70
    ފ
    0.69
    er
    0.68
     تاہم
    0.68
    ità
    0.66
    ibe
    0.66
    ون
    0.66
    Activations Density 0.000%

    No Known Activations