© 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. 7421
    Prev
    Next
    INDEX
    Explanations

    caused by, focused on, suited for, inspired by

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects quantitative comparisons and statistical or numeric information (e.g. words signaling measurements, differences, or “than,” “mean,” “point,” “significantly,” etc.).

    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
    ってる
    1.30
    してる
    1.20
     kinda
    1.16
     sorta
    1.16
     kiddos
    1.15
     तपाई
    1.14
     uptick
    1.11
    됬
    1.08
     বললো
    1.05
     গেলো
    1.03
    POSITIVE LOGITS
     physicochemical
    1.09
     irrespective
    1.03
     hitherto
    1.02
     invariably
    1.01
     potentialities
    1.00
    あるいは
    0.99
    又は
    0.98
     physico
    0.91
     нередко
    0.90
    itherto
    0.89
    Activations Density 0.114%

    No Known Activations