© 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. 78950
    Prev
    Next
    INDEX
    Explanations

    prominent scholars and 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
     haram
    -0.77
     sağlar
    -0.74
    onias
    -0.73
    ギャラリー
    -0.72
     liturgy
    -0.70
     Geste
    -0.70
    専用の
    -0.69
    enor
    -0.69
    seys
    -0.69
     Kv
    -0.68
    POSITIVE LOGITS
     scholars
    1.49
     scholar
    1.28
     Scholars
    1.20
    scholars
    1.06
    scholar
    1.05
     revival
    1.02
    Scholars
    1.02
     Scholar
    0.96
     scholarly
    0.92
    deposit
    0.90
    Activations Density 0.028%

    No Known Activations