© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12939
    Prev
    Next
    INDEX
    Explanations

    word endings

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

    This neuron detects names of specialized fields or disciplines (e.g., academic, professional, or technical domains).

    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
     D
    0.74
    T
    0.71
    at
    0.69
    para
    0.68
    to
    0.68
    ah
    0.66
    for
    0.65
    ab
    0.65
    so
    0.65
    h
    0.64
    POSITIVE LOGITS
    者は
    0.91
     doctrines
    0.89
     adalah
    0.87
    들은
    0.86
     είναι
    0.84
     encompasses
    0.81
     embodies
    0.80
    是一种
    0.79
     являются
    0.79
     arose
    0.77
    Activations Density 0.297%

    No Known Activations