© 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. 211152
    Prev
    Next
    INDEX
    Explanations

    X versus Y constructs

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

    speaking or technical terms

    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
    ^{*}\
    0.46
    dire
    0.46
     lâm
    0.46
     abrió
    0.46
     parois
    0.46
     Heel
    0.46
     করিবার
    0.45
     खोला
    0.44
     başlad
    0.44
     વિકાસ
    0.44
    POSITIVE LOGITS
    ت
    0.63
    이
    0.52
     โอเค
    0.49
    一
    0.48
    Ка
    0.48
     garner
    0.47
    цыю
    0.47
    అ
    0.47
    م
    0.46
    т
    0.44
    Activations Density 0.000%

    No Known Activations