© 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. 5476
    Prev
    Next
    INDEX
    Explanations

    generating content based on instructions

    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
    ادي
    0.98
    usura
    0.96
    ícia
    0.96
    彳
    0.96
    上記の
    0.92
     لڑکی
    0.89
     može
    0.88
    کیل
    0.87
    様の
    0.86
     cerveza
    0.86
    POSITIVE LOGITS
     Environ
    2.03
    contents
    2.01
    aining
    1.99
     Autumn
    1.97
     coverings
    1.96
     Saeed
    1.93
     INTRODUCTION
    1.91
     containing
    1.89
     解
    1.89
     Covering
    1.87
    Activations Density 0.101%

    No Known Activations