© 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. 213
    Prev
    Next
    INDEX
    Explanations

    The neuron is tuned to detect numeric expressions (e.g. quantities, measurements, or other numbers) in the text.

    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
    0.41
    <0x0D>
    0.29
    1
    0.26
    3
    0.25
    4
    0.25
    }
    0.23
    0.23
    0
    0.22
      
    0.22
    -
    0.22
    POSITIVE LOGITS
     มัน
    0.31
     یہ
    0.31
     اگر
    0.30
    它
    0.30
     यह
    0.30
    มัน
    0.30
     těch
    0.30
    這些
    0.29
     ადამიან
    0.29
     تلك
    0.29
    Activations Density 1.597%

    No Known Activations