© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 15495
    Prev
    Next
    INDEX
    Explanations

    AM and Toilet Man

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

    The neuron fires most strongly on the principal predicate of a clause—i.e. the main verb (or its phrasal‐verb particle) in a sentence.

    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
     ､
    0.76
     刺繍
    0.75
     自
    0.68
     Bên
    0.66
    ına
    0.65
    വണ
    0.65
     গার্মেন্টস
    0.65
    慜
    0.64
     バック
    0.63
     ڈاؤن
    0.62
    POSITIVE LOGITS
    soldiers
    0.91
    b
    0.91
     inciner
    0.87
    bbi
    0.85
     varient
    0.84
    alchemy
    0.83
     chimiques
    0.82
    😢
    0.82
    contraction
    0.81
    v
    0.79
    Activations Density 0.000%

    No Known Activations