© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 85868
    Prev
    Next
    INDEX
    Explanations

    Talmud and Jewish law

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

    The neuron fires strongly on named entities in the rabbinic/Jewish-legal domain—titles of texts (e.g. “Talmud,” “Bava Basra,” “Eruvin,” “Mishnah”), the names of commentators or authorities (e.g. “Rashi,” “Rambam,” “Geonim”), and related place- or person names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Their
    -1.76
    匍
    -1.72
     knap
    -1.42
    تفصیلات
    -1.38
     hintergrund
    -1.37
    嘏
    -1.36
    龶
    -1.36
     című
    -1.35
    {\
    -1.33
    京城
    -1.30
    POSITIVE LOGITS
    1
    1.91
     Bedarf
    1.51
    '
    1.47
    ًا
    1.45
    
    1.42
     Spazier
    1.40
    The
    1.34
    It
    1.33
    même
    1.32
    ())){
    1.32
    Activations Density 0.005%

    No Known Activations