© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64270
    Prev
    Next
    INDEX
    Explanations

    titles of creative works

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

    The neuron activates on words naming or describing creative‐arts media and events (e.g. plays, films, books, musical works, performances, awards, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     zama
    -1.14
     lojas
    -1.14
    自分の
    -1.13
     ilustraciones
    -1.08
    messung
    -1.07
     primeiras
    -1.07
     mesmas
    -1.07
    啐
    -1.05
    ※
    -1.03
    剧情
    -1.02
    POSITIVE LOGITS
    zzlies
    1.07
     Let
    1.06
    IPPI
    1.05
    Quir
    1.04
     Side
    1.03
    avajillas
    1.03
    常见的
    1.02
    नलोड
    1.00
    Beij
    1.00
     Сен
    1.00
    Activations Density 0.013%

    No Known Activations