© 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. 10167
    Prev
    Next
    INDEX
    Explanations

    quartic partitions

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

    This neuron primarily activates on multi‐digit numeric tokens (e.g. file or figure numbers, statistical values, and other long numerical identifiers).

    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
     நிற
    0.62
    싹
    0.58
    oldCount
    0.57
     woord
    0.57
    股东
    0.57
     ausgesch
    0.57
    toadd
    0.57
    抢
    0.57
     جشن
    0.56
     Elevations
    0.56
    POSITIVE LOGITS
    Ki
    0.59
    Andrew
    0.54
     iki
    0.53
    QK
    0.53
    Aqu
    0.52
    CQ
    0.52
    ki
    0.52
     MB
    0.51
    SCHEMA
    0.51
    Ку
    0.49
    Activations Density 0.012%

    No Known Activations