© 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. 187724
    Prev
    Next
    INDEX
    Explanations

    different conclusions, ruby code, disciples of, terribly, needing to, we could

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

    programming language keywords

    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
     in
    0.58
     contag
    0.48
    슨
    0.48
    在
    0.47
     with
    0.47
     contagious
    0.46
     Cardiovascular
    0.44
     Title
    0.44
    鐘
    0.44
     contagion
    0.44
    POSITIVE LOGITS
     ඔබට
    0.60
     sadrž
    0.60
     効果
    0.51
    mprj
    0.50
    BASIC
    0.49
    رین
    0.49
    まれた
    0.49
    鳎
    0.49
     বিধান
    0.48
     njima
    0.48
    Activations Density 0.001%

    No Known Activations