© 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. 190864
    Prev
    Next
    INDEX
    Explanations

    use reasonable, value rate

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

    human value and rights

    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
     voilà
    0.48
    เข้า
    0.47
     `<`,
    0.46
     নিকটে
    0.45
     voila
    0.44
     Treasurer
    0.44
     글로
    0.44
     Máy
    0.44
     Royce
    0.43
    ितीय
    0.43
    POSITIVE LOGITS
    人的
    0.54
    จัดการ
    0.54
     соблю
    0.48
    嵌
    0.48
    ざ
    0.48
    esen
    0.47
    ент
    0.45
    ação
    0.44
    μός
    0.43
    еры
    0.43
    Activations Density 0.000%

    No Known Activations