© 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. 2104
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly responds to numeric tokens (e.g. numbers in statistics, URLs, or large counts).

    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
    ูนย์
    0.85
    ์
    0.78
     hog
    0.75
    köz
    0.75
    Inet
    0.75
     whopping
    0.74
    Jax
    0.72
    NaOMe
    0.72
     függvény
    0.71
    outgoing
    0.71
    POSITIVE LOGITS
     Proceeds
    0.70
    肪
    0.67
     martyrs
    0.67
    ত
    0.67
    圆
    0.67
     costa
    0.65
    ଚ
    0.65
     Africans
    0.64
     Death
    0.64
     satellites
    0.63
    Activations Density 0.000%

    No Known Activations