© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 5469
    Prev
    Next
    INDEX
    Explanations

    cutoff date

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

    The neuron primarily activates on the word “open,” i.e. instructions or UI prompts telling the user to click or select “open.”

    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
    λώ
    0.72
     V
    0.71
     detections
    0.70
     夏
    0.68
    吨
    0.68
     getActivity
    0.68
     Y
    0.67
    riting
    0.67
    拉
    0.67
     P
    0.66
    POSITIVE LOGITS
     opção
    0.92
    habitude
    0.88
    installment
    0.87
    ຈະ
    0.87
    🤌
    0.86
     Nueva
    0.86
     expressão
    0.86
    fired
    0.84
    
    0.84
    fueled
    0.84
    Activations Density 0.002%

    No Known Activations