© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118804
    Prev
    Next
    INDEX
    Explanations

    religious beliefs and institutions

    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_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
    ・・・・・・・・
    -0.95
     alza
    -0.88
    どうしよう
    -0.88
     vienas
    -0.87
     the
    -0.85
    ホント
    -0.81
     verkauft
    -0.81
     ilman
    -0.81
    クーポン
    -0.81
    量の
    -0.80
    POSITIVE LOGITS
     faith
    1.26
     religion
    1.21
     belief
    1.17
    ism
    1.14
     tradition
    1.08
     ਵਿੱਚ
    0.96
    ätigung
    0.96
     sect
    0.96
     theology
    0.95
    徒
    0.94
    Activations Density 0.029%

    No Known Activations