© 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. 31-GEMMASCOPE-2-RES-16K
    7. 1985
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on code‐style identifiers and technical constants (variable names, function or macro names, file‐extension tokens, etc.).

    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
    3
    0.66
    F
    0.66
    4
    0.66
    posição
    0.65
    R
    0.65
    0
    0.64
    b
    0.64
    p
    0.62
    f
    0.61
    |
    0.61
    POSITIVE LOGITS
     सफलतापूर्वक
    0.66
    हरू
    0.63
     outpouring
    0.61
     Esq
    0.60
     Subhanahu
    0.59
     ナチュラル
    0.58
     leveraging
    0.57
     ajan
    0.57
    ؑ
    0.57
     ພວກເຮົາ
    0.56
    Activations Density 0.010%

    No Known Activations