© 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. 16270
    Prev
    Next
    INDEX
    Explanations

    specific sentence fill-in

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

    The neuron is highly active on tokens in passages that directly address the reader (e.g. “you,” “we,” marketing or instructional “we”/“you” statements).

    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
    h
    0.86
     caspase
    0.81
     bmw
    0.76
     dài
    0.75
     trailer
    0.74
     disney
    0.74
    max
    0.73
     mao
    0.73
     '',
    0.72
     %``
    0.72
    POSITIVE LOGITS
     Бү
    0.72
     інших
    0.69
     Responses
    0.69
     fdPar
    0.67
     relatifs
    0.67
     Einwilligung
    0.67
     Yardım
    0.67
     produktów
    0.66
    AntiForgery
    0.66
     ئەم
    0.65
    Activations Density 0.003%

    No Known Activations