© 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. 11055
    Prev
    Next
    INDEX
    Explanations

    electrical currents for efficient, fast movement

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

    The neuron is a positional detector that activates in proportion to a token’s position (i.e. it tracks where you are in the document).

    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
    )、
    0.95
    datos
    0.95
    ק
    0.93
     financieros
    0.89
    특별시
    0.89
    Fract
    0.87
    /***
    0.86
    Ф
    0.84
    シリ
    0.83
    DIM
    0.80
    POSITIVE LOGITS
     invasions
    0.80
     officials
    0.75
     robbers
    0.73
     neigh
    0.70
     separate
    0.69
     kesel
    0.68
    भद्र
    0.68
     tied
    0.68
     stolen
    0.68
     resten
    0.68
    Activations Density 0.000%

    No Known Activations