Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 99
    Prev
    Next
    INDEX
    Explanations

    movie and film reviews

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     albums
    -0.84
     sax
    -0.83
     television
    -0.83
     Supporters
    -0.79
     designers
    -0.75
     foliar
    -0.75
     phono
    -0.75
     Albums
    -0.74
    tv
    -0.71
    midt
    -0.70
    POSITIVE LOGITS
     movie
    2.03
     Movie
    1.81
    Movie
    1.67
    movie
    1.65
     film
    1.48
    映画
    1.45
    電影
    1.45
     кино
    1.42
     movies
    1.38
     MOVIE
    1.36
    Activations Density 0.023%

    No Known Activations