© 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. 6493
    Prev
    Next
    INDEX
    Explanations

    Michigan and Eminem

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

    This neuron activates on numeric expressions (e.g. standalone digits, multi-digit numbers, and numerical 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_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
     Lhasa
    0.71
     Wessex
    0.65
    PQ
    0.63
     Joko
    0.60
     कर्नाटक
    0.58
    🐨
    0.58
     Bogotá
    0.57
    NSW
    0.57
    বুদ্ধ
    0.57
    儒
    0.57
    POSITIVE LOGITS
     Michigan
    2.36
    Michigan
    2.30
     Detroit
    2.22
    Detroit
    2.20
     MICHIGAN
    2.00
     Saginaw
    1.87
     गुजरात
    1.80
     Kalamazoo
    1.65
    गुजरात
    1.59
     Gujarat
    1.55
    Activations Density 0.423%

    No Known Activations