© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9208
    Prev
    Next
    INDEX
    Explanations

    site and scene locations

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

    location and safety assessment

    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_40_width_16k_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
     chiqar
    0.44
     যাত্রী
    0.39
    进来
    0.37
     nowhere
    0.37
    ামের
    0.37
     ക്ലാ
    0.37
    避
    0.36
     হারবাল
    0.36
     Appearing
    0.36
    鍏
    0.36
    POSITIVE LOGITS
    现场
    2.16
     site
    2.08
    現場
    2.08
     scene
    2.03
    site
    1.85
    scene
    1.78
    Site
    1.73
     Site
    1.73
    SITE
    1.62
     Scene
    1.61
    Activations Density 0.297%

    No Known Activations