© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93194
    Prev
    Next
    INDEX
    Explanations

    Church of England

    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
     Scopus
    -0.77
     Μα
    -0.77
     effluent
    -0.75
    험
    -0.75
    RK
    -0.75
     запро
    -0.75
     Informatics
    -0.75
    {{--
    -0.74
    entrum
    -0.74
    chae
    -0.72
    POSITIVE LOGITS
     England
    1.05
     Anglican
    0.93
    England
    0.86
    england
    0.85
     Formular
    0.81
    kolor
    0.79
     england
    0.77
     Additional
    0.74
     Canterbury
    0.73
     régle
    0.71
    Activations Density 0.044%

    No Known Activations