© 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. 1250
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on numeric tokens and quantitative expressions (e.g. numbers, statistics, measurements, or quantities).

    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
    quando
    1.26
    Quando
    1.25
    Cuando
    1.19
     quando
    1.12
     когда
    1.10
     cuando
    1.09
    when
    1.09
    当
    1.09
     حين
    1.08
    cuando
    1.08
    POSITIVE LOGITS
     throughout
    1.01
     annually
    0.75
     lately
    0.72
     this
    0.71
     overtime
    0.68
     today
    0.66
     over
    0.66
     alike
    0.66
     anytime
    0.64
     traditionally
    0.64
    Activations Density 0.551%

    No Known Activations