© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10750
    Prev
    Next
    INDEX
    Explanations

    imaginary unit i

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

    The neuron activates on numeric tokens, especially floating‐point numbers or measurements.

    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
     majors
    0.73
    s
    0.71
     kullanıl
    0.70
    utiliser
    0.65
    Spawner
    0.64
     vign
    0.63
     사용할
    0.63
     leptons
    0.62
     قیامت
    0.62
    ᱟ
    0.62
    POSITIVE LOGITS
    led
    0.91
    pping
    0.90
     extraordinarily
    0.79
     thrilled
    0.78
    ling
    0.77
     crystallized
    0.77
     Всем
    0.76
    чают
    0.75
     perpetually
    0.74
    িয়াছি
    0.74
    Activations Density 0.000%

    No Known Activations