© 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. 4606
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on the word “putter.”

    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
     chuyện
    0.84
    вной
    0.76
    ೕ
    0.75
     confirms
    0.75
     слы
    0.73
     underestimates
    0.73
     بسرعة
    0.73
    魧
    0.73
     undermines
    0.72
     быстро
    0.71
    POSITIVE LOGITS
    ند
    0.77
     ainsi
    0.75
     Allgemeinen
    0.75
     Gerardo
    0.73
    platz
    0.72
    اج
    0.71
     dernières
    0.71
     sitzen
    0.71
     "\\"
    0.70
    ]">
    0.70
    Activations Density 0.000%

    No Known Activations