© 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. 12737
    Prev
    Next
    INDEX
    Explanations

    significant

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

    The neuron detects “©” copyright notices or the “(c)” token in legal/license text.

    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
     заместитель
    0.95
     células
    0.87
    ING
    0.84
    nement
    0.84
    り
    0.84
     trein
    0.82
     práticas
    0.82
    tól
    0.81
    tım
    0.79
    retirement
    0.79
    POSITIVE LOGITS
    ل
    0.89
    ્લે
    0.79
    ozione
    0.74
    다른
    0.73
    ્વ
    0.71
    لل
    0.71
    olni
    0.71
    ו
    0.71
     alba
    0.70
     scant
    0.70
    Activations Density 0.000%

    No Known Activations