© 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. 6673
    Prev
    Next
    INDEX
    Explanations

    can be

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

    This neuron fires on present‐participle or gerund forms—that is, tokens ending in “-ing.”

    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
    t
    1.17
    l
    1.05
    า
    0.98
     wodurch
    0.98
    enable
    0.94
    ic
    0.91
    invalidate
    0.90
    potentially
    0.90
    tir
    0.89
    有可能
    0.89
    POSITIVE LOGITS
     archery
    1.06
     manis
    1.05
    𝐺
    1.03
     toiletries
    1.02
     archbishop
    1.02
     archivos
    1.02
     bishops
    1.01
     finalists
    1.01
     kanssa
    1.01
     twenties
    1.00
    Activations Density 0.002%

    No Known Activations