© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38132
    Prev
    Next
    INDEX
    Explanations

    film and movie related content

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

    This neuron fires on title‐style or headline tokens—especially capitalized words at the start of a news headline or section heading.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    caric
    -0.84
     Retail
    -0.79
    kowy
    -0.77
    Retail
    -0.76
    нив
    -0.73
    WebServlet
    -0.73
    solver
    -0.73
    Yaml
    -0.72
    杂志
    -0.72
     álbum
    -0.72
    POSITIVE LOGITS
     film
    3.92
     films
    3.31
    film
    3.16
     movie
    3.16
     Film
    3.16
     filmmakers
    2.98
    Film
    2.97
     movies
    2.80
     cinema
    2.67
     Films
    2.61
    Activations Density 0.179%

    No Known Activations