© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 1858
    Prev
    Next
    INDEX
    Explanations

    of America, Ascension, Thrones

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

    This neuron fires on the head noun that appears immediately before “of” in “X of Y” constructions (e.g. “Fog of War,” “arc of sight,” “ring of Kerry”).

    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_31_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
    ЛЬ
    0.53
    1
    0.52
    ஸ்தான
    0.51
     얘기
    0.51
    сё
    0.50
    ^^
    0.50
    0
    0.49
    లి
    0.48
    ರ್ಯ
    0.47
    ings
    0.47
    POSITIVE LOGITS
     fabrica
    0.63
     Thrones
    0.58
     Wight
    0.57
     îles
    0.56
     सचिवा
    0.56
     Horus
    0.55
     Eden
    0.54
     Darkness
    0.54
     Americas
    0.52
     uporab
    0.52
    Activations Density 0.646%

    No Known Activations