© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14540
    Prev
    Next
    INDEX
    Explanations

    still or anyway

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

    but still, even if

    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_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
     यासाठी
    0.37
     Česk
    0.37
     जीने
    0.36
     давно
    0.36
     clues
    0.36
    š
    0.36
     арен
    0.35
     macaroni
    0.35
     competent
    0.35
     fogo
    0.35
    POSITIVE LOGITS
     vẫn
    1.98
    依然
    1.92
    仍然
    1.90
    仍
    1.79
    依旧
    1.77
     still
    1.75
     STILL
    1.73
    still
    1.69
     fortfarande
    1.67
     trotzdem
    1.66
    Activations Density 0.647%

    No Known Activations