© 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. 11292
    Prev
    Next
    INDEX
    Explanations

    symbols and abbreviations

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

    The neuron is highly sensitive to numerical or quantitative information and spikes on mentions of measurements, statistics, or numeric values.

    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
    0.77
    }</
    0.72
    0.72
    0.68
    ುದು
    0.64
    0.61
    0.61
    p
    0.58
    }$
    0.57
    }'
    0.57
    POSITIVE LOGITS
    물을
    0.86
     deliberations
    0.86
    еха
    0.83
     Александра
    0.82
     maîtres
    0.82
     появля
    0.82
    轼
    0.82
    ехать
    0.81
     पहिल्या
    0.80
    вропей
    0.80
    Activations Density 0.000%

    No Known Activations