© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 664
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens—especially decimal numbers or measurements.

    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
     variously
    0.27
     rétrécies
    0.27
     necessitating
    0.26
     víct
    0.25
     designee
    0.24
     elsewhere
    0.24
     :).
    0.24
     pursuant
    0.24
     Öffentlichkeit
    0.24
    䡈
    0.24
    POSITIVE LOGITS
    n
    0.42
    u
    0.38
    m
    0.36
    r
    0.35
    d
    0.34
    I
    0.33
    N
    0.33
    S
    0.32
    U
    0.32
    ных
    0.32
    Activations Density 0.000%

    No Known Activations