© 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. 24-GEMMASCOPE-2-RES-16K
    7. 4398
    Prev
    Next
    INDEX
    Explanations

    This neuron primarily detects and activates on numeric tokens (e.g. list indices, measurements, and other standalone numbers).

    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
    0.83
     này
    0.78
     =
    0.77
    ();
    0.75
     (
    0.74
     и
    0.73
    -
    0.73
    ;
    0.73
    (
    0.73
    this
    0.69
    POSITIVE LOGITS
     سایر
    0.88
     ఇతర
    0.84
     myös
    0.83
     অন্যান্য
    0.82
     أيضا
    0.79
     अन्य
    0.77
     jederzeit
    0.75
     egyéb
    0.75
     മറ്റ്
    0.74
     autres
    0.73
    Activations Density 1.416%

    No Known Activations