© 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. 24-GEMMASCOPE-2-RES-16K
    7. 11361
    Prev
    Next
    INDEX
    Explanations

    conditional logic and operators

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

    This neuron activates on programming-language Boolean expressions, especially null checks and comparison/logic operators (e.g. !=, &&, “is null”).

    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_24_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
    для
    0.85
    untuk
    0.75
     untuk
    0.73
     для
    0.69
    ❏
    0.69
    mfrac
    0.68
    ��������
    0.68
    옮
    0.67
    ________________
    0.66
     kanggo
    0.66
    POSITIVE LOGITS
     नहीं
    1.44
     không
    1.41
     немає
    1.39
     değildir
    1.35
     نہیں
    1.32
     δεν
    1.30
     nicht
    1.29
     není
    1.27
     ikke
    1.26
     ਨਹੀਂ
    1.26
    Activations Density 0.141%

    No Known Activations