© 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. 7332
    Prev
    Next
    INDEX
    Explanations

    own safety filters, custom plugins, own dishes

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

    The neuron fires on occurrences of the word “own.”

    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
    क
    1.16
    dür
    1.09
     i
    1.04
     other
    0.96
     c
    0.95
     o
    0.93
     I
    0.91
     y
    0.91
     Iglesias
    0.91
     UPC
    0.90
    POSITIVE LOGITS
    ל
    1.30
     volition
    1.14
    speople
    1.08
     таки
    1.07
     सफाया
    1.02
    ৯
    1.01
    לות
    1.00
     limitaciones
    0.99
    దన
    0.98
    ことです
    0.98
    Activations Density 0.042%

    No Known Activations