© 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. 5718
    Prev
    Next
    INDEX
    Explanations

    code execution paths

    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
    ek
    1.15
    oner
    1.11
    中期
    1.06
     qu
    1.05
    EK
    1.04
     import
    1.01
    x
    1.00
     undist
    1.00
     back
    1.00
    wich
    1.00
    POSITIVE LOGITS
    Вакансия
    1.44
    findElement
    1.37
    Tight
    1.34
    rescence
    1.31
    的基本
    1.31
     embod
    1.28
    bestos
    1.27
    
    1.27
     tighten
    1.27
    Positions
    1.27
    Activations Density 0.034%

    No Known Activations