© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 10949
    Prev
    Next
    INDEX
    Explanations

    dates and specific section headers

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

    This neuron is primarily looking for the vertical-bar character “|.”

    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
    业内
    0.84
     বিষয়টি
    0.83
     concurso
    0.79
     yalnızca
    0.78
    ຜູ້
    0.77
    ية
    0.76
     ó
    0.76
     múltiples
    0.76
     atractivo
    0.76
    ный
    0.75
    POSITIVE LOGITS
    اید
    0.87
    تقد
    0.80
    7
    0.73
     kinds
    0.70
     lactic
    0.69
     jurisprudence
    0.69
     เมตร
    0.68
    2
    0.66
    Stmt
    0.65
     scared
    0.65
    Activations Density 0.001%

    No Known Activations