© 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. 12778
    Prev
    Next
    INDEX
    Explanations

    sconces, Bartholomew, Eleanor

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

    The neuron fires on the single content word that immediately follows the preposition “for.”

    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
    PHOT
    0.89
    dihydroxy
    0.79
    UNDS
    0.77
     résult
    0.76
    SEED
    0.75
    remmo
    0.75
    ULT
    0.74
    ⺀
    0.74
     inégal
    0.73
    ults
    0.73
    POSITIVE LOGITS
     droid
    0.89
     ejecutivo
    0.86
    ுண்டு
    0.82
    ductory
    0.80
     banjo
    0.80
     duplex
    0.79
     motivator
    0.79
    ke
    0.77
    硗
    0.76
    kező
    0.75
    Activations Density 0.001%

    No Known Activations