© 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. 11984
    Prev
    Next
    INDEX
    Explanations

    The neuron is acting as a “position” detector, firing most strongly on tokens near the very start of each text block.

    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
     มือ
    0.88
    歐
    0.79
     esteja
    0.76
     impacting
    0.75
     elevating
    0.75
    貞
    0.75
    國家
    0.74
    囉
    0.73
    呎
    0.72
     sebaik
    0.72
    POSITIVE LOGITS
     полноцен
    0.74
    g
    0.73
    ne
    0.71
    ną
    0.71
    зывают
    0.69
     nube
    0.68
    ához
    0.67
     columna
    0.66
     neuer
    0.65
     ropa
    0.64
    Activations Density 0.000%

    No Known Activations