© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10948
    Prev
    Next
    INDEX
    Explanations

    Jewish religious texts and concepts

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

    Judaism and related religious terms

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

    Jewish religious terms

    np_max-act-logits · claude-4-5-sonnetTriggered by @sripadkarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_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
     christ
    0.50
     Damn
    0.49
    ✌
    0.47
     creamy
    0.47
     clienti
    0.47
     भारतात
    0.47
     bollywood
    0.46
     ক্যাথোডে
    0.46
     consumables
    0.46
    🤘
    0.45
    POSITIVE LOGITS
     Torah
    1.43
     Rabbi
    1.41
     Shabbat
    1.27
     rabbis
    1.24
     Jewish
    1.17
     rabbi
    1.17
     Pesach
    1.16
    Jewish
    1.14
     Talmud
    1.14
     Shabb
    1.14
    Activations Density 0.171%

    No Known Activations