© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11216
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on floating‐point numbers (numeric tokens containing a decimal point).

    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
    ’
    0.83
    {
    0.69
    Here
    0.69
    '
    0.69
    Matcher
    0.67
     here
    0.67
    _{
    0.66
     여기
    0.66
    _{\
    0.66
    ()
    0.64
    POSITIVE LOGITS
     consensual
    0.85
     multilateral
    0.81
     multiplayer
    0.77
     direção
    0.75
     robberies
    0.73
     global
    0.73
     pastoral
    0.73
     pipelines
    0.72
     marijuana
    0.72
     macroeconomic
    0.71
    Activations Density 0.000%

    No Known Activations