© 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. 469
    Prev
    Next
    INDEX
    Explanations

    elections and financial crises

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

    The neuron activates on numerical tokens, picking up numbers, dates, prices, and other digit‐based expressions.

    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
     SIINFEKL
    0.62
     サイズ
    0.60
     えっと
    0.60
     ቫ
    0.59
    ebly
    0.59
    ayı
    0.58
     với
    0.58
    ilibus
    0.57
     chỉ
    0.57
     мм
    0.57
    POSITIVE LOGITS
     moratorium
    0.50
    American
    0.49
    Secret
    0.49
    Committee
    0.48
     nonprofit
    0.48
    Institute
    0.48
     government
    0.47
    -
    0.47
     federal
    0.46
    Prop
    0.46
    Activations Density 0.000%

    No Known Activations