© 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. 86262
    Prev
    Next
    INDEX
    Explanations

    initiatives, language, port of, heel

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

    removed informal language

    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
    ла
    0.52
     cosidd
    0.45
     Counsel
    0.45
     насыщен
    0.44
    ста
    0.43
    са
    0.43
    氯
    0.43
     sogen
    0.42
     курс
    0.42
     commenced
    0.42
    POSITIVE LOGITS
     ஆண்டுகளில்
    0.47
     societies
    0.47
     வாழ்க்கை
    0.46
    年の
    0.46
     themes
    0.45
    槑
    0.45
     frameworks
    0.44
     Societies
    0.44
     enthusiasts
    0.43
    ไฟฟ้า
    0.42
    Activations Density 0.000%

    No Known Activations