© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 190802
    Prev
    Next
    INDEX
    Explanations

    airport, reinstate, justice, power

    np_acts-logits-general · gemini-2.5-flash-lite

    Nar Shaddaa eliminate Worker Drones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
     وه
    0.48
    Wein
    0.48
     creado
    0.46
    AML
    0.44
    𝖐
    0.44
     创建
    0.43
     集
    0.43
     worsen
    0.43
     Weinstein
    0.42
     worsened
    0.42
    POSITIVE LOGITS
     icons
    0.48
     occupants
    0.47
    З
    0.47
     descriptions
    0.45
    ありました
    0.45
    Пла
    0.45
    hib
    0.45
     experts
    0.45
     personalities
    0.45
    tail
    0.43
    Activations Density 0.000%

    No Known Activations