© 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. 12997
    Prev
    Next
    INDEX
    Explanations

    padded decimal number

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

    The neuron responds strongly to individual content-bearing tokens (uncommon or specialized words) rather than to common function words.

    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
    т
    0.73
    м
    0.73
    ↵
    0.72
    ня
    0.72
    <0xA9>
    0.70
     型
    0.69
    把它
    0.68
     దూర
    0.64
     столь
    0.62
    Ｃ
    0.62
    POSITIVE LOGITS
     politiche
    1.03
    ے
    1.00
     foglie
    0.91
    ústria
    0.87
    urés
    0.87
     berisi
    0.82
     attravers
    0.82
     parlato
    0.81
    وٹ
    0.80
     Público
    0.80
    Activations Density 0.000%

    No Known Activations