© 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. 77524
    Prev
    Next
    INDEX
    Explanations

    teacher and international equivalents

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

    teacher

    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
    リ
    0.61
    キ
    0.55
    フ
    0.54
    シ
    0.51
    ง
    0.49
    デ
    0.48
    갑
    0.48
    จาก
    0.47
    へ
    0.47
    KeyUp
    0.47
    POSITIVE LOGITS
    teacher
    0.68
     учитель
    0.58
     teacher
    0.53
     öğretmen
    0.52
     Routledge
    0.51
     England
    0.50
     Lehrer
    0.50
     laureate
    0.50
     pedag
    0.48
     (!)
    0.48
    Activations Density 0.004%

    No Known Activations