© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87067
    Prev
    Next
    INDEX
    Explanations

    orthodox Jewish communities

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

    The neuron flags document metadata lines—especially date, time, byline, and other header fields (e.g. month/day, author titles, location).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     patriotism
    -0.77
    巽
    -0.77
     ceea
    -0.75
     корпуса
    -0.73
     transfers
    -0.72
     transferred
    -0.72
    MenuInflater
    -0.72
    MarshalTo
    -0.71
    DEZ
    -0.71
     classes
    -0.70
    POSITIVE LOGITS
    Ultra
    1.21
     Orthodox
    1.20
     Ultra
    1.16
     ultra
    1.11
     ortodo
    1.10
     orthodox
    1.07
     Amish
    1.05
     Hare
    1.00
     Williamsburg
    0.96
     Yiddish
    0.95
    Activations Density 0.012%

    No Known Activations