© 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. 202136
    Prev
    Next
    INDEX
    Explanations

    unique words or entities

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

    API, GPU, Gaming, Topology, Detection

    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
    он
    0.57
    ωσ
    0.52
    وبر
    0.52
    osk
    0.52
    ويب
    0.52
    оп
    0.52
    녠
    0.52
    àn
    0.52
    сла
    0.52
     крас
    0.52
    POSITIVE LOGITS
     strongly
    0.52
    Side
    0.48
            
    0.46
     troops
    0.46
     truly
    0.46
         
    0.45
     obtained
    0.45
          
    0.44
     United
    0.44
     peak
    0.44
    Activations Density 0.000%

    No Known Activations