© 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. 11854
    Prev
    Next
    INDEX
    Explanations

    calculated

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

    The neuron activates on numeric tokens (especially numbers and decimal values).

    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
     mohou
    0.71
    ழ்
    0.65
    כ
    0.62
     madd
    0.61
     blijkt
    0.61
     wynika
    0.59
     může
    0.59
    ∃
    0.59
     mycorrh
    0.57
     worsens
    0.57
    POSITIVE LOGITS
    굵
    0.67
     Riccardo
    0.66
     الكهربائيه
    0.66
    temperatur
    0.66
     ઘરે
    0.65
    zigzag
    0.65
     സമയ
    0.64
    จาก
    0.64
    细腻
    0.63
    setMaximum
    0.63
    Activations Density 0.000%

    No Known Activations