© 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. 74270
    Prev
    Next
    INDEX
    Explanations

    teach or impart knowledge

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

    education and learning concepts

    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
    ✼
    0.48
    ━━━━
    0.46
    洪
    0.45
    স্বামী
    0.45
    tickers
    0.45
    最低
    0.44
    گن
    0.44
     वर्चुअल
    0.44
    จ
    0.43
    ◟
    0.43
    POSITIVE LOGITS
     eğitim
    0.58
     education
    0.57
     giáo
    0.55
     haver
    0.55
     Bildung
    0.54
     vzděl
    0.52
     impar
    0.52
     functionally
    0.52
     Judo
    0.52
     angling
    0.51
    Activations Density 0.000%

    No Known Activations