© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 8448
    Prev
    Next
    INDEX
    Explanations

    Recruitment, recurrent, recursion, reciprocal

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

    This neuron detects word fragments containing the “rec” prefix (e.g. recapture, record, recruit, recaps).

    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
    なく
    0.61
    нии
    0.58
    anée
    0.57
     справ
    0.57
     Сле
    0.56
    荊
    0.55
    焼け
    0.55
    厈
    0.54
     Sick
    0.54
    на
    0.54
    POSITIVE LOGITS
     Rec
    1.38
     REC
    1.33
    REC
    1.30
    Rec
    1.30
    rec
    1.29
     rec
    1.08
     rek
    1.03
    iprocal
    0.96
    Reco
    0.95
     reco
    0.90
    Activations Density 0.198%

    No Known Activations