© 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. 5156
    Prev
    Next
    INDEX
    Explanations

    list types

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

    This neuron detects the angle‐bracket token “<” when used in code (e.g. in generic type parameters or template/list syntax).

    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
    ب
    1.78
    بك
    1.36
    م
    1.19
    بق
    1.12
    vency
    1.03
    بخ
    1.02
    нд
    1.02
    oporosis
    1.00
    м
    0.99
    ج
    0.99
    POSITIVE LOGITS
    Uint
    0.82
    एम
    0.81
     Affirm
    0.77
    Violation
    0.76
     kiếm
    0.75
    ats
    0.75
     وبين
    0.75
    ado
    0.73
    >()
    0.71
    ել
    0.71
    Activations Density 0.000%

    No Known Activations