© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5479
    Prev
    Next
    INDEX
    Explanations

    large dollar amounts (millions/billions)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    ames
    1.72
    模拟
    1.65
    чения
    1.61
    mainWindow
    1.60
     soldering
    1.59
     dissect
    1.58
     coment
    1.58
    仿
    1.56
     hist
    1.56
     chronology
    1.55
    POSITIVE LOGITS
    bevel
    1.31
    serr
    1.30
     Bestellung
    1.28
     endorsements
    1.21
    จ่าย
    1.20
    vdots
    1.15
    一级
    1.13
    zai
    1.13
    earn
    1.12
    million
    1.12
    Activations Density 0.063%

    No Known Activations