© 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. 5391
    Prev
    Next
    INDEX
    Explanations

    rug, Mug, Case, pad, peg, Bed, Organizer, brushes, head, wash

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

    This neuron detects concrete nouns naming consumer products or household items.

    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
    Mi
    0.73
    Of
    0.67
    ⚖
    0.67
    ()
    0.66
    Principles
    0.63
    性の
    0.62
    外国
    0.62
    議論
    0.62
    IPv
    0.61
    
    0.61
    POSITIVE LOGITS
     cushions
    0.79
     skewers
    0.79
     conditioner
    0.74
     utensils
    0.73
     bushings
    0.72
     bumpers
    0.71
     аксессу
    0.70
     concealer
    0.70
     bushing
    0.69
     ornaments
    0.68
    Activations Density 0.136%

    No Known Activations