© 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. 115840
    Prev
    Next
    INDEX
    Explanations

    Catholic ancestors

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

    Ctrl + Shift + T

    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
     Свет
    0.49
     свет
    0.47
     ειδ
    0.46
     фото
    0.46
    િત
    0.44
     де
    0.43
    пет
    0.43
    揭
    0.43
    人气
    0.42
    ônica
    0.42
    POSITIVE LOGITS
    Philosophy
    0.55
    んですよ
    0.52
     Philosophy
    0.50
     दुनियाभर
    0.49
     Procurement
    0.48
    Medicare
    0.47
    ាទ
    0.47
     philosophy
    0.47
     Postgraduate
    0.47
     ہوگا۔
    0.46
    Activations Density 0.000%

    No Known Activations