© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68307
    Prev
    Next
    INDEX
    Explanations

    titles in quotes

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

    This neuron fires on the opening of a quoted title of a creative work (movie, song, book, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     plafon
    -2.00
     花纹
    -1.88
     peluche
    -1.88
     zodia
    -1.88
     multicolore
    -1.84
     pantalon
    -1.83
     descarga
    -1.75
     kado
    -1.73
     alternatif
    -1.73
     coreano
    -1.72
    POSITIVE LOGITS
    and
    1.89
     all
    1.77
     All
    1.76
     more
    1.74
     J
    1.73
     The
    1.72
     In
    1.72
     Only
    1.64
     To
    1.63
     Like
    1.63
    Activations Density 0.017%

    No Known Activations