© 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. 2756
    Prev
    Next
    INDEX
    Explanations

    in this parallel real Python various

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

    The neuron activates on instances of the preposition “in” immediately followed by a numeric expression (e.g. years or other numbers).

    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
     ໃນ
    0.59
     인
    0.57
     陳
    0.57
     ใน
    0.56
     ง
    0.55
     ン
    0.55
     คน
    0.54
     เป
    0.54
    AMOUNT
    0.54
     คูณ
    0.53
    POSITIVE LOGITS
     collaboration
    0.71
     lesquels
    0.70
     workshops
    0.64
     collaborations
    0.60
     amelyek
    0.60
     which
    0.60
     hopes
    0.59
     които
    0.59
     colaboración
    0.59
     cooperation
    0.59
    Activations Density 0.296%

    No Known Activations