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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 9458
    Prev
    Next
    INDEX
    Explanations

    religious organizations and beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zky
    1.33
    ienten
    1.10
    ب
    1.09
     تث
    1.08
    ซ์
    1.07
    ِينَ
    1.07
     immer
    1.06
     line
    1.05
    зер
    1.05
    Ł
    1.02
    POSITIVE LOGITS
     religiosas
    2.16
     sects
    2.15
     sectarian
    2.10
     religión
    2.01
     appease
    2.00
     मस्जिद
    1.98
     shrines
    1.98
     católica
    1.96
    宗教
    1.92
     religious
    1.91
    Activations Density 0.403%

    No Known Activations