© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11149
    Prev
    Next
    INDEX
    Explanations

    keywords, search terms, commands

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

    The neuron fires strongly on the central topic keywords or head nouns that label each section’s subject.

    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_31_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
    ERICAN
    0.66
    UAGE
    0.66
     Utilization
    0.64
     থাকিলে
    0.64
    ^{*}}\
    0.63
     Ủ
    0.61
     Service
    0.60
    দ্যাল
    0.59
    SERVICE
    0.59
     Skill
    0.59
    POSITIVE LOGITS
     купить
    1.23
     kopen
    0.98
     kaufen
    0.97
    <u>
    0.96
    口コミ
    0.93
    <strong>
    0.88
     отзывы
    0.85
    <b>
    0.83
     wiki
    0.81
    ⁤
    0.79
    Activations Density 1.201%

    No Known Activations