© 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
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 15885
    Prev
    Next
    INDEX
    Explanations

    The neuron flags programming‐oriented tokens—identifiers, API/class/type names, code keywords, and other developer jargon.

    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_31_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
    Localized
    0.60
     Vans
    0.55
     Localization
    0.54
    LocalizedString
    0.53
    ([
    0.52
    accumulation
    0.51
    یث
    0.50
     enhances
    0.50
     Mutant
    0.50
     localized
    0.50
    POSITIVE LOGITS
    managedbuild
    0.57
    éto
    0.56
     func
    0.53
    弱
    0.53
    !(
    0.52
    IBAction
    0.52
     berat
    0.52
    UpInside
    0.52
    的同时
    0.51
    🚂
    0.51
    Activations Density 0.002%

    No Known Activations