© 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
    2. Gemma-3-12B
    3. 31-GEMMASCOPE-2-RES-16K
    4. 10747
    Prev
    Next
    INDEX
    Explanations

    module

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

    The neuron activates on references to Apache “mod_…” modules and related module filenames or paths (e.g. mod_deflate, mod_security, modules/filters, 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
     जी
    0.63
     ilość
    0.59
     $\
    0.57
     Krak
    0.56
     pa
    0.55
     misty
    0.55
     Ji
    0.54
     ক্ষ
    0.54
     uptime
    0.54
     obtus
    0.53
    POSITIVE LOGITS
    🚲
    0.61
    pmod
    0.59
    moduleId
    0.58
    Modular
    0.55
    modulo
    0.55
    🏍
    0.54
    مود
    0.54
    وابة
    0.53
     модуль
    0.53
     AppModule
    0.53
    Activations Density 0.004%

    No Known Activations