© 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. 77029
    Prev
    Next
    INDEX
    Explanations

    Anglican church matters

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

    describing observations and questions

    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
    स्टूड
    0.52
    シティ
    0.52
     সন্ত্রাসী
    0.51
     શહેર
    0.50
    γκα
    0.50
    τζ
    0.48
    ἂ
    0.47
    soundcloud
    0.47
    🌆
    0.47
     міста
    0.46
    POSITIVE LOGITS
     Michaelmas
    0.59
     Anglican
    0.57
     in
    0.56
     Lincolnshire
    0.53
     ecclesiastical
    0.53
     Dorset
    0.51
     episcopal
    0.50
     vicar
    0.49
     Shetland
    0.48
     eccles
    0.47
    Activations Density 0.001%

    No Known Activations