© 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. 19982
    Prev
    Next
    INDEX
    Explanations

    University and technology

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

    university and related suffixes

    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
    จากการ
    0.49
    keV
    0.44
    lept
    0.41
    विड
    0.41
    /")
    0.41
    。”
    0.41
    尺寸
    0.40
    𝗗
    0.40
    单个
    0.40
    插件
    0.40
    POSITIVE LOGITS
     University
    0.66
     universidades
    0.65
     Universitas
    0.64
     university
    0.63
     universities
    0.63
     Universidade
    0.62
     Universities
    0.60
     université
    0.60
     Université
    0.60
     университета
    0.60
    Activations Density 0.067%

    No Known Activations