© 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. 10801
    Prev
    Next
    INDEX
    Explanations

    The neuron fires strongly on words that begin sentences—that is, tokens in sentence‐initial position.

    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
     limpia
    0.79
     nghĩa
    0.77
    wości
    0.75
    odoris
    0.74
     stos
    0.73
     jTextField
    0.70
    tım
    0.68
    ἀ
    0.68
    ylsulfanyl
    0.68
     pictureBox
    0.68
    POSITIVE LOGITS
    IST
    0.80
     তিনজন
    0.77
     அறிந்த
    0.71
    并在
    0.70
    ியது
    0.70
    ية
    0.68
    IAN
    0.68
    BI
    0.67
     підпри
    0.66
    Office
    0.66
    Activations Density 0.000%

    No Known Activations