© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12990
    Prev
    Next
    INDEX
    Explanations

    Zoroastrianism

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

    The neuron strongly activates on numeric tokens (digit sequences and numbers, including multi‐digit and decimal values) found in references and citations.

    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_31_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
    عو
    0.59
    捶
    0.57
    鑽
    0.56
    صح
    0.51
    節目
    0.51
     Suit
    0.50
     Chik
    0.50
     حی
    0.50
    例
    0.50
    তীশ
    0.50
    POSITIVE LOGITS
    localized
    0.61
    lbrack
    0.57
     அல்லாஹ்
    0.56
    declar
    0.55
     அல்லாஹ்வின்
    0.55
     localized
    0.54
    сию
    0.52
     quantum
    0.52
    defs
    0.52
    が出る
    0.52
    Activations Density 0.010%

    No Known Activations