© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21602
    Prev
    Next
    INDEX
    Explanations

    Christians

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

    The neuron activates on mentions of “Christian” or “Christians.”

    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
    larda
    -2.36
     amaze
    -2.13
     agility
    -2.11
     
    -2.11
     enlarging
    -2.06
     soo
    -2.05
     eloquent
    -2.05
     adorable
    -2.03
    z
    -2.02
    en
    -1.93
    POSITIVE LOGITS
    from
    2.45
    沵
    2.36
    }
    2.33
    坼
    2.23
    茔
    2.22
    鹟
    2.20
    鹮
    2.19
    倻
    2.17
    ⚣
    2.11
    呖
    2.09
    Activations Density 0.002%

    No Known Activations