© 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. 12196
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens (e.g. integers or decimal 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
     picker
    0.76
     retainer
    0.75
    ្សា
    0.75
    ម្បី
    0.73
    オシャレ
    0.73
    кре
    0.72
     BAC
    0.72
    п
    0.70
     duration
    0.70
     sofern
    0.69
    POSITIVE LOGITS
    Kid
    0.92
     sebuah
    0.91
    Aula
    0.89
     Almighty
    0.87
    kau
    0.86
     Aank
    0.85
    wealth
    0.83
    God
    0.83
    Gee
    0.83
    he
    0.82
    Activations Density 0.000%

    No Known Activations