© 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. 9223
    Prev
    Next
    INDEX
    Explanations

    breast size

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

    The neuron fires strongly on the sentence‐ or clause‐final content word just before a punctuation break.

    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
    ãy
    0.88
    긋
    0.81
    rollback
    0.80
    Pedido
    0.79
    dok
    0.77
     kaldır
    0.77
     nosotros
    0.77
    简介
    0.77
    쌤
    0.75
    Pessoal
    0.75
    POSITIVE LOGITS
     Excellency
    0.70
    ਹਾ
    0.68
    једина
    0.67
     onOptions
    0.66
     localities
    0.66
     COMPONENTS
    0.62
     municipalities
    0.61
     Speakers
    0.60
     elevationMap
    0.60
     himself
    0.60
    Activations Density 0.000%

    No Known Activations