© 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. 31-GEMMASCOPE-2-RES-16K
    7. 10501
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on multi‐word proper names (titles of programs, campaigns, organizations, etc.).

    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
     scholar
    0.76
    野
    0.75
     photographer
    0.75
    年
    0.75
    됐다
    0.74
    らった
    0.72
    రోజు
    0.72
     educator
    0.71
     Transaction
    0.71
    日
    0.71
    POSITIVE LOGITS
     тобто
    0.77
    רי
    0.66
     assolutamente
    0.65
     warped
    0.64
     ตำ
    0.64
     робити
    0.63
     mildly
    0.62
    inerja
    0.62
    ндарт
    0.62
     ordinate
    0.62
    Activations Density 0.000%

    No Known Activations