© 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. 2024
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily detects numerical expressions—monetary figures, measurements, percentages, and other quantitative 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_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
    .
    0.60
    ’
    0.58
    ?
    0.58
    !
    0.57
    Delete
    0.56
    '.
    0.54
    ).
    0.53
    c
    0.53
    '
    0.53
    z
    0.52
    POSITIVE LOGITS
     ingestion
    0.66
     urbanization
    0.65
     aerodynamics
    0.64
     alertness
    0.64
     electromagnetic
    0.61
     lubrication
    0.61
    大きさ
    0.61
     predation
    0.59
     expediency
    0.59
     abiotic
    0.59
    Activations Density 0.087%

    No Known Activations