© 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. 99607
    Prev
    Next
    INDEX
    Explanations

    made available or

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

    offer free Wi-Fi

    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
     şirket
    0.55
    
    0.50
     время
    0.50
     কোম্পানি
    0.49
     მარ
    0.48
     शॉपिंग
    0.48
    ósfera
    0.48
     kır
    0.48
    牍
    0.47
     하게
    0.46
    POSITIVE LOGITS
    tab
    0.46
    ol
    0.44
    pop
    0.44
    isSelected
    0.43
    int
    0.43
    or
    0.43
    Tab
    0.42
    tm
    0.41
    IL
    0.41
    ENO
    0.41
    Activations Density 0.000%

    No Known Activations