© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9194
    Prev
    Next
    INDEX
    Explanations

    order book, pulse mode, public key

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

    The neuron primarily detects tokens containing numeric characters (e.g. numbers, dates, measurements, codes).

    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
     anemia
    1.04
    𝙚
    0.91
     auricular
    0.88
     attuned
    0.86
     непотпу
    0.86
    मैट
    0.86
     calmed
    0.85
     Ayurvedic
    0.83
     ousted
    0.83
     ステン
    0.82
    POSITIVE LOGITS
    0.77
    ح
    0.75
    지
    0.74
    RET
    0.71
    ંગ
    0.70
    Michael
    0.70
    First
    0.69
    Tor
    0.68
      
    0.68
    خ
    0.67
    Activations Density 0.000%

    No Known Activations