© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3412
    Prev
    Next
    INDEX
    Explanations

    university context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    人形
    0.81
     gyerek
    0.79
    ścia
    0.79
     childlike
    0.78
     çocuğ
    0.74
    叠
    0.74
     Mensch
    0.73
     குழந்தைகளுக்கு
    0.73
    儿童
    0.72
    噼
    0.71
    POSITIVE LOGITS
     university
    2.90
     campus
    2.72
     universities
    2.64
    Faculty
    2.57
     Faculty
    2.54
    Campus
    2.53
    University
    2.52
     University
    2.50
    university
    2.49
     Universities
    2.49
    Activations Density 0.230%

    No Known Activations