© 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. 5431
    Prev
    Next
    INDEX
    Explanations

    am designed to

    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
    身为
    1.39
    isance
    1.39
    ítmény
    1.39
    禀
    1.39
     resistência
    1.38
     resiliency
    1.28
    毙
    1.28
     firmness
    1.27
    usetzen
    1.27
    ravity
    1.26
    POSITIVE LOGITS
    ❼
    1.72
    َب
    1.57
     waypoint
    1.57
    OGEN
    1.56
     Origins
    1.56
     textbox
    1.55
     Arac
    1.53
     ☐
    1.53
     Prague
    1.52
    ⓪
    1.52
    Activations Density 0.007%

    No Known Activations