© 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. 40029
    Prev
    Next
    INDEX
    Explanations

    connected parts

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

    system comprises

    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
    軼
    0.50
     preclude
    0.48
     потен
    0.48
     immunological
    0.47
    髖
    0.47
     potenciales
    0.47
     heretofore
    0.46
     motivic
    0.46
    옇
    0.45
    經驗
    0.45
    POSITIVE LOGITS
     ऑफिस
    0.51
     YouTuber
    0.51
     Ninja
    0.50
     Ubuy
    0.48
     Carlos
    0.48
     लीजिएगा
    0.47
     Outs
    0.47
     Raul
    0.47
    ड़िया
    0.46
     Usman
    0.46
    Activations Density 0.004%

    No Known Activations