© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9139
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting numeric expressions (quantities, measurements, 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_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
    znych
    1.19
    mck
    1.17
    ان
    1.15
    leges
    1.09
    ieken
    1.06
    prache
    0.98
    べて
    0.97
    誨
    0.95
    an
    0.95
     generaciones
    0.94
    POSITIVE LOGITS
     Weight
    1.47
     weight
    1.30
    Weight
    1.20
     batteries
    1.20
     weights
    1.19
     calories
    1.15
    weight
    1.13
    WEIGHT
    1.13
     enthalpy
    1.11
     WEIGHT
    1.09
    Activations Density 2.933%

    No Known Activations