© 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. 204242
    Prev
    Next
    INDEX
    Explanations

    about what

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

    mix or choose options

    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
     ប
    0.51
    ק
    0.50
     (
    0.50
    indoor
    0.49
    ​
    0.49
    (-
    0.48
    ()
    0.47
     in
    0.47
     SPC
    0.47
      
    0.45
    POSITIVE LOGITS
    मर्श
    0.52
    什么是
    0.50
    াবলীর
    0.47
    关于
    0.46
     bagaimana
    0.46
     bestseller
    0.46
     desafio
    0.46
     défis
    0.46
    介紹
    0.46
     serem
    0.46
    Activations Density 0.004%

    No Known Activations