© 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. 4329
    Prev
    Next
    INDEX
    Explanations

    box

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

    The neuron detects formal legal‐license or copyright terms (e.g., “prior,” “authorization,” “owner,” “author”) in disclaimer and rights‐statement passages.

    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
    ulfite
    0.84
    orphous
    0.79
    getBytes
    0.79
    ềm
    0.78
    }{*}{
    0.78
    óf
    0.78
     semicolon
    0.78
     colonized
    0.77
    miş
    0.77
     colonization
    0.77
    POSITIVE LOGITS
    天津
    0.86
    على
    0.85
    י
    0.81
    HALL
    0.80
    ي
    0.79
    কর
    0.74
     розта
    0.70
    ا
    0.68
     оце
    0.68
    परि
    0.68
    Activations Density 0.001%

    No Known Activations