© 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. 2473
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily responds to numeric tokens (e.g. section numbers, quantities, years).

    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
     symbolize
    0.79
    데
    0.74
     philosophers
    0.71
     shortlist
    0.71
    땃
    0.70
     Prophets
    0.70
     philos
    0.69
     inhabit
    0.69
     源
    0.68
     captains
    0.68
    POSITIVE LOGITS
    𝑟
    0.84
    at
    0.83
    array
    0.75
    icom
    0.73
    obutyl
    0.72
    eye
    0.71
    end
    0.71
    ched
    0.70
    endlich
    0.70
    ens
    0.70
    Activations Density 0.000%

    No Known Activations