© 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. 10-GEMMASCOPE-RES-131K
    7. 70304
    Prev
    Next
    INDEX
    Explanations

    movie genres and titles

    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_10/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
    omenclature
    -1.22
     exportación
    -1.19
     verschieden
    -1.18
     großem
    -1.13
     irgendwann
    -1.12
     Ausführungen
    -1.12
    reds
    -1.11
     vieler
    -1.10
    cets
    -1.09
     regalías
    -1.09
    POSITIVE LOGITS
     then
    1.45
    ̳
    1.34
     or
    1.23
     sitten
    1.21
    oraus
    1.11
     kanske
    1.07
     melaksanakan
    1.07
     даже
    1.07
     entonces
    1.06
    然后
    1.05
    Activations Density 0.186%

    No Known Activations