© 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. 154230
    Prev
    Next
    INDEX
    Explanations

    ceremonial, ritual, solemn, monument

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

    social materiality and ritualistic structures

    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
     rozwoju
    0.46
     развития
    0.46
    艨
    0.46
     DEVELOPMENT
    0.44
    開發
    0.44
    ওয়ার
    0.44
     influ
    0.43
     разработки
    0.43
     জো
    0.43
    ɵ
    0.43
    POSITIVE LOGITS
     ceremonial
    0.54
     solemn
    0.50
    仪式
    0.48
     sumptuous
    0.43
     ceremon
    0.42
     monument
    0.41
     solemnly
    0.41
     Bernstein
    0.41
    ritual
    0.40
     Crem
    0.40
    Activations Density 0.023%

    No Known Activations