© 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. 24-GEMMASCOPE-2-RES-16K
    7. 911
    Prev
    Next
    INDEX
    Explanations

    The neuron consistently spikes on the word “be.”

    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
    inston
    0.88
     fragen
    0.80
    entuk
    0.77
    ك
    0.77
     selanjutnya
    0.77
    uskan
    0.75
    lsulfanyl
    0.75
     kesempatan
    0.74
     größ
    0.73
    vić
    0.73
    POSITIVE LOGITS
    er
    0.90
    에
    0.80
    ার
    0.75
    сен
    0.74
    зи
    0.74
    で
    0.74
    歟
    0.73
    인
    0.73
     repressed
    0.73
    le
    0.72
    Activations Density 0.017%

    No Known Activations