© 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. 11347
    Prev
    Next
    INDEX
    Explanations

    The neuron is essentially detecting the word “board.”

    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
     zásobníku
    0.76
     panjang
    0.74
    ennies
    0.71
    ר
    0.71
    りの
    0.70
    děpodob
    0.67
    ctree
    0.67
    აციის
    0.66
    apunov
    0.66
     prepd
    0.66
    POSITIVE LOGITS
    ب
    0.93
     wichtigen
    0.81
     Brands
    0.80
    お知らせ
    0.79
    Brands
    0.79
    お客
    0.78
     Autoren
    0.78
     Breathe
    0.76
    Remarks
    0.75
    該当
    0.75
    Activations Density 0.000%

    No Known Activations