© 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. 9040
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric tokens, particularly measurement values and other 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_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
    誂
    0.63
     টাকায়
    0.61
     حول
    0.61
     Limits
    0.60
     ভাষায়
    0.58
    ামা
    0.56
     Hồ
    0.56
    ፈር
    0.56
     Анг
    0.56
     متوسط
    0.56
    POSITIVE LOGITS
     difference
    1.04
    difference
    1.02
    差
    1.00
     différence
    0.98
     increments
    0.97
     diferença
    0.97
    extra
    0.96
     margin
    0.96
     extra
    0.95
    Difference
    0.95
    Activations Density 0.480%

    No Known Activations