© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 57443
    Prev
    Next
    INDEX
    Explanations

    pilgrims and devotees

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

    pilgrimage sites and travelers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    小学校
    0.47
     উদ্ভাব
    0.45
    ären
    0.43
    გენ
    0.43
    辞典
    0.42
     Verbre
    0.42
    寯
    0.40
    ปร
    0.40
    ElementChild
    0.40
    齬
    0.40
    POSITIVE LOGITS
     pilgrimage
    1.47
     pilgrims
    1.43
     pilgr
    1.32
     pilgrim
    1.23
     Pilgr
    1.20
     तीर्थ
    1.00
     श्रद्धालुओं
    0.96
     श्रद्धालु
    0.96
     பக்தர்கள்
    0.91
     devotees
    0.88
    Activations Density 0.053%

    No Known Activations