© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 31298
    Prev
    Next
    INDEX
    Explanations

    touristy places

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thoroughbred
    0.47
    s
    0.47
    quinoline
    0.44
    diamine
    0.44
     huwa
    0.44
    <unused689>
    0.44
    يات
    0.44
     hà
    0.44
     DVD
    0.43
     применя
    0.43
    POSITIVE LOGITS
    叶
    0.47
    根
    0.46
    星座
    0.46
    न
    0.44
    質問
    0.44
    神奇
    0.44
    {%
    0.42
     stessi
    0.42
    四
    0.42
    ন
    0.42
    Activations Density 0.006%

    No Known Activations