© 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. 14001
    Prev
    Next
    INDEX
    Explanations

    facial recognition

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

    The neuron fires on words ending in “-er” or “-or” that name people or things performing an action (agent-noun endings).

    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
    が多く
    0.83
     deviceInfo
    0.82
    が決
    0.81
    ર
    0.81
    が増
    0.79
    ورسٹی
    0.78
    ுள்ளது
    0.77
     Lately
    0.76
    甠
    0.76
    لوك
    0.75
    POSITIVE LOGITS
    ිර
    0.74
     shall
    0.74
     bribery
    0.73
     two
    0.68
     eyewitness
    0.68
    a
    0.66
     তৎকালীন
    0.66
     words
    0.65
     sad
    0.65
     condemnation
    0.65
    Activations Density 0.001%

    No Known Activations