© 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. 2023
    Prev
    Next
    INDEX
    Explanations

    The neuron is highly sensitive to quantitative contexts, i.e. passages conveying numbers, measurements, or statistical data.

    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
    ública
    0.60
    assertSame
    0.59
    ứa
    0.57
    ógio
    0.56
    improve
    0.55
    newNode
    0.55
    さんに
    0.55
    
    0.55
     एकज
    0.55
    を行い
    0.54
    POSITIVE LOGITS
     नहीं
    2.09
     نہیں
    1.97
     ਨਹੀਂ
    1.89
     nicht
    1.88
     tidak
    1.88
     neither
    1.85
     немає
    1.82
     नही
    1.81
    नहीं
    1.74
     ikke
    1.73
    Activations Density 0.756%

    No Known Activations