© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 12338
    Prev
    Next
    INDEX
    Explanations

    p: legions, steering, models

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

    The neuron is tuned to detect numeric expressions—tokens representing numbers, counts, measurements, or years.

    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
    Wt
    0.89
    澼
    0.84
    Unless
    0.82
    Vx
    0.80
    пикир
    0.79
    ➤
    0.77
    Type
    0.76
    Serie
    0.76
    gün
    0.76
    ע
    0.76
    POSITIVE LOGITS
     healers
    0.86
    ادر
    0.85
     misappropri
    0.80
     Tibetan
    0.77
     neoliberal
    0.76
     गठित
    0.76
     Malawi
    0.75
     secession
    0.75
     insurrection
    0.74
     violin
    0.74
    Activations Density 0.001%

    No Known Activations