© 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. 70608
    Prev
    Next
    INDEX
    Explanations

    movie titles and names

    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
     faciliter
    -1.98
     corriger
    -1.86
    votre
    -1.85
    鹩
    -1.84
     poë
    -1.84
     magnific
    -1.74
     your
    -1.74
     ekip
    -1.70
     foton
    -1.69
     accompagner
    -1.67
    POSITIVE LOGITS
     more
    2.53
     for
    2.33
     less
    2.09
     with
    2.08
     three
    2.02
     after
    1.94
     not
    1.93
     as
    1.93
     in
    1.88
     four
    1.83
    Activations Density 0.090%

    No Known Activations