© 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. 5135
    Prev
    Next
    INDEX
    Explanations

    alternative conjunctions

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

    This neuron fires on domain-specific keywords—i.e. technical or topic-specific content words (jargon) across a variety of contexts.

    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
     据
    0.81
    其中包括
    0.80
     inclu
    0.78
     જેમાં
    0.77
    بول
    0.77
    此外
    0.76
    据悉
    0.75
    详细
    0.74
    挍
    0.74
    詳細
    0.72
    POSITIVE LOGITS
     ataupun
    1.01
     yoki
    1.01
     vagy
    1.00
     või
    1.00
     или
    0.99
    或者
    0.98
     atau
    0.97
     nebo
    0.95
     কিংবা
    0.95
     किंवा
    0.95
    Activations Density 2.797%

    No Known Activations