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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 539
    Prev
    Next
    INDEX
    Explanations

    religious terms and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ’
    -2.64
     was
    -2.47
    可以选择
    -2.41
     freaking
    -2.28
    节日
    -2.23
    が終わ
    -2.17
    珵
    -2.16
    窳
    -2.14
     *
    -2.14
    .'
    -2.13
    POSITIVE LOGITS
    狆
    2.95
    !”
    2.70
     zusätz
    2.69
     vollständ
    2.66
    姈
    2.61
     間取り
    2.53
    Ꮵ
    2.53
    禤
    2.52
     erstes
    2.48
    มัน
    2.45
    Activations Density 0.004%

    No Known Activations