© 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. 78904
    Prev
    Next
    INDEX
    Explanations

    Islamic religious figures

    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
    Postup
    -0.85
    MenuInflater
    -0.76
    TERNS
    -0.73
     ruinous
    -0.73
    Elizabeth
    -0.71
    settings
    -0.69
    coltà
    -0.69
     بغداد
    -0.69
    ßt
    -0.68
     airbag
    -0.68
    POSITIVE LOGITS
     Companions
    1.14
     hypo
    1.02
     Migration
    1.02
     companions
    1.01
     Revelation
    0.97
    compan
    0.94
     Abu
    0.92
     Companion
    0.90
    Revelation
    0.89
     Hypo
    0.88
    Activations Density 0.017%

    No Known Activations