© 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. 14023
    Prev
    Next
    INDEX
    Explanations

    numbers, questions, or values

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

    The neuron strongly activates on tokens that start a new sentence or segment.

    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
    c
    0.87
    та
    0.86
    ar
    0.86
    u
    0.85
    n
    0.81
     וכ
    0.77
    pal
    0.72
    ind
    0.71
    it
    0.70
    Ã
    0.70
    POSITIVE LOGITS
     réalisée
    0.95
    ुलर
    0.90
    ្នាំ
    0.89
     carbides
    0.88
     présentée
    0.88
     रिप्रे
    0.88
    오늘
    0.87
    Hasil
    0.87
     réalisées
    0.87
     représent
    0.86
    Activations Density 0.000%

    No Known Activations