© 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. 15260
    Prev
    Next
    INDEX
    Explanations

    multilingual religious and academic contexts

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

    The neuron responds to uncommon capitalized words or named entities (i.e. proper nouns).

    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
    呖
    -3.97
    瓩
    -2.91
    ⼭
    -2.80
    ⽩
    -2.53
    ಿ
    -2.53
    ке
    -2.50
     апреля
    -2.44
    趵
    -2.39
    秾
    -2.39
    ⭓
    -2.39
    POSITIVE LOGITS
    '
    3.44
     verbess
    3.13
     Our
    3.00
     sogen
    2.52
    ↵↵
    2.50
     
    2.45
     besonderes
    2.41
    --
    2.41
     kleines
    2.36
     ganzes
    2.30
    Activations Density 0.006%

    No Known Activations