© 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. 14238
    Prev
    Next
    INDEX
    Explanations

    words related to programming structure

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

    The neuron fires on numerical values with decimal points (measurements, statistics, or other floating-point numbers).

    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
    к
    0.89
    व
    0.86
    ﮭ
    0.85
    گ
    0.84
    ھ
    0.81
    ג
    0.81
    ک
    0.79
     revêtu
    0.78
    س
    0.78
    с
    0.77
    POSITIVE LOGITS
     anhydride
    0.80
     sampel
    0.79
    ‍♂️
    0.74
    samples
    0.73
    nem
    0.73
    liğini
    0.72
    sets
    0.71
    nate
    0.71
    nge
    0.71
     появление
    0.70
    Activations Density 0.000%

    No Known Activations