© 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. 34-GEMMASCOPE-RES-131K
    7. 64491
    Prev
    Next
    INDEX
    Explanations

    religious and biblical concepts

    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
     executing
    -0.89
     executed
    -0.80
    シルバー
    -0.75
    fieur
    -0.75
    simov
    -0.74
    tricos
    -0.72
    jší
    -0.72
    riques
    -0.71
     executes
    -0.71
     atypical
    -0.70
    POSITIVE LOGITS
     lukewarm
    0.98
     Smyrna
    0.80
    Revelation
    0.77
     Philadelphia
    0.76
    Gemeinde
    0.76
     gemeente
    0.74
     Gemeinde
    0.74
     Revelation
    0.74
     Philadel
    0.73
     gemeenten
    0.71
    Activations Density 0.002%

    No Known Activations