© 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. 2285
    Prev
    Next
    INDEX
    Explanations

    official founding

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

    The neuron fires on numeric tokens—especially multi‐digit numbers and numeric expressions (years, counts, 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
    ễ
    0.57
     воздей
    0.57
    кови
    0.56
     отклю
    0.56
     BLUENRG
    0.55
     लौट
    0.55
    ễm
    0.55
    ahmatullahi
    0.54
    に入れる
    0.54
     ['(?
    0.54
    POSITIVE LOGITS
     founded
    2.94
     Founded
    2.86
     founding
    2.83
    Founded
    2.72
    founded
    2.64
     founders
    2.53
     تأس
    2.41
     Founding
    2.39
     founder
    2.38
     설립
    2.38
    Activations Density 0.763%

    No Known Activations