© 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. 7272
    Prev
    Next
    INDEX
    Explanations

    is a

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

    This neuron detects the definitional “is a” (or “was a”) phrase that introduces an entity’s type in an encyclopedic description.

    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
     newbies
    0.75
    RE
    0.75
     boasts
    0.70
     RE
    0.70
     boasting
    0.70
     này
    0.68
     tummy
    0.68
    🆚
    0.67
     this
    0.66
     contrário
    0.65
    POSITIVE LOGITS
     американский
    0.78
     अमेर
    0.74
     Ghanaian
    0.73
     美国
    0.72
     американ
    0.72
     ehemalige
    0.71
     ऑस्ट्रेलियाई
    0.71
     அமெரிக்க
    0.70
     polskich
    0.70
     미국의
    0.69
    Activations Density 0.006%

    No Known Activations