© 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. 832
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric literal tokens (e.g. integers or floating‐point constants) in code snippets.

    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
     Omphalodes
    0.60
     résoudre
    0.55
     bluntly
    0.51
     dépour
    0.51
     Göttingen
    0.50
     Jeśli
    0.49
    ilmiş
    0.49
    鴟
    0.49
     Sélection
    0.49
     Côte
    0.49
    POSITIVE LOGITS
    _
    0.84
     =
    0.61
     is
    0.49
    ']=$
    0.48
    \_
    0.47
    ="";
    0.45
    isNull
    0.45
    <unused62>
    0.43
    data
    0.43
    ='';
    0.43
    Activations Density 0.011%

    No Known Activations