© 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. 34-GEMMASCOPE-RES-131K
    7. 55715
    Prev
    Next
    INDEX
    Explanations

    IMDb or IMDB entries

    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
     evacuation
    -0.84
    BuilderFactory
    -0.79
     عسل
    -0.75
     Belarusian
    -0.73
     NSFW
    -0.72
     Parra
    -0.70
    mson
    -0.70
    pielt
    -0.68
     slur
    -0.67
    Inquiry
    -0.66
    POSITIVE LOGITS
     IMDb
    3.47
     IMDB
    3.17
    imdb
    2.80
     imdb
    2.59
    IMDb
    2.56
     IM
    2.39
    IMDB
    2.33
     Im
    1.99
    Im
    1.81
    IM
    1.66
    Activations Density 0.056%

    No Known Activations