© 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. 24-GEMMASCOPE-2-RES-16K
    7. 6388
    Prev
    Next
    INDEX
    Explanations

    git clone --recursive

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

    The neuron detects mentions of specific legal, governmental, or institutional entities and provisions (e.g. names of Acts, Committees, regulatory bodies, and official rules).

    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
     clín
    0.61
     communicator
    0.59
     operativa
    0.59
     chirp
    0.57
     günlük
    0.56
    报告
    0.55
     VHF
    0.55
     accelerometer
    0.54
     gamepad
    0.54
    userAgent
    0.54
    POSITIVE LOGITS
     কিংবা
    0.81
     ഏത
    0.77
     Sedangkan
    0.77
     либо
    0.76
     অথবা
    0.76
    หรือไม่
    0.72
     或者
    0.71
     Messrs
    0.70
     혹은
    0.70
    或者是
    0.70
    Activations Density 0.112%

    No Known Activations