© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6941
    Prev
    Next
    INDEX
    Explanations

    restrictions and temporary files

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

    The neuron activates on numeric expressions (prices, percentages, measurements, or other numbers) in 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
    s
    1.01
    y
    1.01
    ik
    0.92
    k
    0.87
     N
    0.85
    t
    0.85
     Kag
    0.82
     in
    0.82
    g
    0.80
     นี้
    0.80
    POSITIVE LOGITS
    цы
    0.96
    меры
    0.94
     ثالث
    0.88
    ным
    0.86
    ры
    0.84
    торы
    0.82
    менты
    0.82
    ды
    0.80
    readonly
    0.80
    Ended
    0.80
    Activations Density 0.001%

    No Known Activations