Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-65K
    4. 3781
    Prev
    Next
    INDEX
    Explanations

    Catholicism

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wrangler
    0.77
    和田
    0.76
     Epit
    0.65
     Sampson
    0.64
     Sasuke
    0.63
    ⠊
    0.62
     alanine
    0.60
     Elli
    0.60
     Rusland
    0.60
    ▽
    0.59
    POSITIVE LOGITS
     Catholic
    2.65
    Catholic
    2.57
     Catholics
    2.49
     Catholicism
    2.15
     catholic
    2.14
     Jesuit
    2.02
     Vatican
    1.96
     católica
    1.94
     Jesuits
    1.83
     catholique
    1.79
    Activations Density 0.061%

    No Known Activations