© 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. 101734
    Prev
    Next
    INDEX
    Explanations

    religious and historical periods

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

    historian of byzantine and islamic empires

    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
     ఆధ్యా
    0.49
    闿
    0.47
    殓
    0.47
     тради
    0.46
    Wedgwood
    0.46
    荇
    0.45
     బ్రిటి
    0.45
    🧅
    0.45
     সফদর
    0.45
     czerwca
    0.45
    POSITIVE LOGITS
     Byzant
    0.65
     Byzantine
    0.61
     Constantinople
    0.55
     Abbas
    0.53
     AD
    0.51
     monastic
    0.50
     Christian
    0.49
     Sts
    0.48
     apud
    0.47
     Antioch
    0.47
    Activations Density 0.062%

    No Known Activations