© 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
    5. 29-GEMMASCOPE-2-RES-16K
    7. 166
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_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
     KeyEvent
    0.66
     오류
    0.65
     resultante
    0.64
     무게
    0.64
    setGeometry
    0.64
    ของการ
    0.63
    ಶ
    0.62
     数据
    0.62
    BarStyle
    0.62
    constraintStart
    0.62
    POSITIVE LOGITS
     friends
    3.70
     friend
    3.29
    friends
    3.11
     relatives
    3.03
     cousins
    3.00
    朋友
    2.93
     buddies
    2.92
     siblings
    2.88
     acquaintances
    2.85
     girlfriends
    2.80
    Activations Density 2.776%

    No Known Activations