© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 64560
    Prev
    Next
    INDEX
    Explanations

    Spirit of God

    np_acts-logits-general · gemini-2.5-flash-lite

    spirit and its contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    騙
    0.48
     बैचलर्स
    0.48
    明星
    0.47
     телеви
    0.47
    一天
    0.46
     करिएगा
    0.46
    אי
    0.46
    🏨
    0.46
    პი
    0.45
     парази
    0.45
    POSITIVE LOGITS
     Spirit
    0.79
     Espíritu
    0.68
    Spirit
    0.68
    spirit
    0.68
     spirit
    0.67
     Spirits
    0.61
     espírito
    0.59
     Espírito
    0.56
     espíritu
    0.56
     spirits
    0.54
    Activations Density 0.041%

    No Known Activations