© 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. 2682
    Prev
    Next
    INDEX
    Explanations

    font names or emoji

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

    The neuron is tuned to spot numeric and statistical information—numbers, percentages, counts, and related quantitative data in specifications or reports.

    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
     kuchen
    0.89
     уничто
    0.82
    p
    0.80
     reik
    0.79
    ្នាំ
    0.79
     administrar
    0.78
     nimet
    0.78
     eben
    0.76
     प्रबल
    0.76
     solver
    0.76
    POSITIVE LOGITS
    י
    0.88
    Vous
    0.81
    Gracias
    0.79
    Poppins
    0.77
    이를
    0.76
    Hola
    0.75
    Displayed
    0.75
    Emojis
    0.75
    ি
    0.75
    Honestly
    0.75
    Activations Density 0.009%

    No Known Activations