© 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. 6789
    Prev
    Next
    INDEX
    Explanations

    `setlocal` variable assignment in batch files

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

    The neuron is triggered by decimal‐formatted numbers (i.e. floating‐point numerals).

    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
    -
    0.71
    ↵
    0.70
    _
    0.68
    /
    0.68
    os
    0.65
    ISI
    0.65
    osi
    0.63
    .
    0.62
     –
    0.61
     government
    0.61
    POSITIVE LOGITS
     Kylie
    0.95
    \|,
    0.93
    Фото
    0.92
    bending
    0.90
    ﺢ
    0.87
     για
    0.86
    𝓼
    0.86
    蒉
    0.85
     Verbind
    0.85
    ᱓
    0.84
    Activations Density 0.001%

    No Known Activations