© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 13641
    Prev
    Next
    INDEX
    Explanations

    end of, even if, mid

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

    The neuron is primarily triggered by numeric tokens—especially multi‐digit numbers, decimal values, and page or citation references.

    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
    exports
    0.74
    it
    0.73
    Lip
    0.73
    lip
    0.69
    us
    0.68
    .
    0.68
    *
    0.66
    rt
    0.66
    lng
    0.65
     amoureux
    0.65
    POSITIVE LOGITS
    груп
    1.05
     proveedores
    1.04
     componentes
    1.02
     간단
    0.98
     системы
    0.97
    ваны
    0.95
     angenommen
    0.93
     dni
    0.93
     acog
    0.92
     foundational
    0.91
    Activations Density 0.000%

    No Known Activations