© 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. 5344
    Prev
    Next
    INDEX
    Explanations

    milk and cream

    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
    ๖
    1.64
    ใต้
    1.59
     правил
    1.54
     endpoints
    1.51
    nodemon
    1.51
     too
    1.50
    nese
    1.49
    (",
    1.49
     sns
    1.49
    ۶
    1.49
    POSITIVE LOGITS
     Singer
    0.79
     Alfvén
    0.79
     Hochsch
    0.76
    nivers
    0.76
     schen
    0.75
     ))
    0.74
    oloč
    0.73
     便利
    0.72
     رز
    0.72
     université
    0.70
    Activations Density 0.065%

    No Known Activations