© 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. 24-GEMMASCOPE-2-RES-16K
    7. 15213
    Prev
    Next
    INDEX
    Explanations

    film festival

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

    The neuron strongly activates on formal descriptions of policy or practice measures—i.e. passages that lay out concrete actions, recommendations, or organized interventions.

    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
     sinnv
    0.75
    док
    0.72
    globin
    0.70
    從小
    0.64
    грамм
    0.61
     alleine
    0.61
     technisch
    0.61
     arguably
    0.60
    从小
    0.60
    кан
    0.59
    POSITIVE LOGITS
     Kazakhstan
    1.14
     Kharkiv
    1.02
     Lithuania
    1.02
     attentively
    1.02
     Ukrainian
    0.99
     Lithuanian
    0.98
     Azerbaijani
    0.98
     Andrey
    0.98
     Kazakh
    0.96
     Moldova
    0.95
    Activations Density 0.991%

    No Known Activations