© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 69026
    Prev
    Next
    INDEX
    Explanations

    documentary films and filmmakers

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

    documentary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     цилинд
    0.47
     dị
    0.45
     வித்திய
    0.45
     минус
    0.44
    ुत
    0.43
     syll
    0.42
    を満
    0.42
    ྪ
    0.42
    িন্ন
    0.42
     приветствую
    0.42
    POSITIVE LOGITS
     documentary
    1.34
     Documentary
    1.28
     documentaries
    1.24
     documentaire
    1.12
     documental
    1.09
     filmmakers
    1.05
     filmmaker
    1.04
     डॉक्यूमेंट्री
    0.97
     Filmm
    0.86
     film
    0.85
    Activations Density 0.152%

    No Known Activations