© 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. 15982
    Prev
    Next
    INDEX
    Explanations

    imitating or borrowing from existing

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

    The neuron strongly responds to action‐oriented gerund verbs (words ending in “-ing” that describe steps or procedures).

    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
     Heute
    0.88
     Sebuah
    0.88
     отдельно
    0.78
    говари
    0.77
     буду
    0.74
    ovaniyu
    0.73
     fuese
    0.72
    쪘
    0.72
     jornada
    0.71
     jovens
    0.71
    POSITIVE LOGITS
     from
    1.09
    from
    1.07
    借鉴
    1.07
    copied
    1.04
    文献
    1.02
    옛
    1.00
     borrowed
    0.98
    จาก
    0.96
     scripture
    0.96
    มาจาก
    0.96
    Activations Density 2.110%

    No Known Activations