© 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. 11339
    Prev
    Next
    INDEX
    Explanations

    measurements in meters and feet

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

    The neuron activates on numeric measurement tokens (especially decimals and other number strings).

    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
    3
    1.02
    8
    0.88
    7
    0.88
    6
    0.87
    4
    0.87
    5
    0.86
    9
    0.86
    2
    0.84
    1
    0.84
    0
    0.75
    POSITIVE LOGITS
     аксессу
    0.83
     professionale
    0.77
     benutzer
    0.77
     accesorios
    0.73
    जेदार
    0.73
     progett
    0.73
     канце
    0.73
     actualizaciones
    0.72
     профессиона
    0.71
    ត្រូវការ
    0.71
    Activations Density 0.030%

    No Known Activations