© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42893
    Prev
    Next
    INDEX
    Explanations

    introducing contrast or exceptions

    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
     that
    -1.78
     we
    -1.76
     it
    -1.73
     you
    -1.58
     the
    -1.49
     there
    -1.41
     Sucher
    -1.39
     rodillas
    -1.38
     everything
    -1.37
     they
    -1.36
    POSITIVE LOGITS
     a
    1.55
     However
    1.49
    釙
    1.40
     however
    1.37
     Conversely
    1.34
    GEBUR
    1.30
    香蕉
    1.29
    鹪
    1.28
    However
    1.28
     школе
    1.27
    Activations Density 0.030%

    No Known Activations