© 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. 31-GEMMASCOPE-2-RES-16K
    7. 12934
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily activates on statistical notation, especially percent signs (%) and related parenthetical numeric expressions.

    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
     Soud
    0.68
    .}$
    0.66
    АСС
    0.66
    각형
    0.66
    टिक
    0.64
    ěstí
    0.64
     тыс
    0.64
     Европа
    0.64
     Stad
    0.63
    \}.
    0.63
    POSITIVE LOGITS
     perspiration
    0.72
    েরও
    0.68
    ाह
    0.68
    ئین
    0.68
     fewer
    0.64
    مک
    0.63
     (!)
    0.61
    Cotton
    0.61
     uptime
    0.61
    ্ডি
    0.61
    Activations Density 0.092%

    No Known Activations