© 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. 5811
    Prev
    Next
    INDEX
    Explanations

    grouping and context

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron is a positional counter that fires strongest on tokens near the start of a document and gradually decreases its activation as you move further into the text.

    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
     sages
    0.77
     পাল্টা
    0.77
    ساس
    0.74
     হৈ
    0.73
     fittings
    0.73
    ొప్ప
    0.73
     ঋ
    0.72
     Aurang
    0.71
     間
    0.70
     epit
    0.70
    POSITIVE LOGITS
    DON
    0.84
    ME
    0.81
    änder
    0.81
    І
    0.81
    MY
    0.80
    Hace
    0.80
    ΜΑ
    0.80
    ó
    0.80
    ussion
    0.79
     cientos
    0.79
    Activations Density 0.000%

    No Known Activations