© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 124038
    Prev
    Next
    INDEX
    Explanations

    under

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

    typed data on websites

    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
    ())+
    0.53
    nilvadipine
    0.49
    সঙ্ঘ
    0.49
     вибра
    0.48
    ுள்ளார்
    0.46
    
    0.45
    ✙
    0.45
     таки
    0.45
     божо
    0.45
    办理
    0.44
    POSITIVE LOGITS
     mily
    0.48
     ini
    0.48
     startup
    0.46
     it
    0.46
    k
    0.45
     investors
    0.45
     rata
    0.44
    াহার
    0.43
     Treaty
    0.43
     o
    0.43
    Activations Density 0.000%

    No Known Activations