© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1144
    Prev
    Next
    INDEX
    Explanations

    technical explanations and definitions

    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
    
    0.93
    \
    0.87
     FAU
    0.86
     
    0.83
     Maus
    0.83
     ug
    0.82
     \
    0.81
     Collapse
    0.80
    ⚫
    0.78
    \\"
    0.77
    POSITIVE LOGITS
    <i>
    2.26
    <em>
    2.06
    넷
    1.09
    ondas
    1.06
    般
    0.99
    āl
    0.97
    atham
    0.95
    <s>
    0.95
    <sub>
    0.95
    routing
    0.94
    Activations Density 0.730%

    No Known Activations