© 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. 86991
    Prev
    Next
    INDEX
    Explanations

    project directories

    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
     Why
    -0.85
     several
    -0.84
     should
    -0.80
     thuận
    -0.76
     require
    -0.75
     despite
    -0.75
     supplement
    -0.74
     requires
    -0.73
    CTE
    -0.71
     how
    -0.71
    POSITIVE LOGITS
    Views
    2.02
     views
    1.96
     Views
    1.86
    views
    1.41
     viewpoints
    1.39
    Pages
    1.36
    Areas
    1.24
    src
    1.14
     VIEWS
    1.12
     Pages
    1.10
    Activations Density 0.004%

    No Known Activations