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

    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-it/resid_post/layer_40_width_16k_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
    闓
    0.42
    दर्
    0.38
     Safe
    0.36
    alamualaikum
    0.36
     aham
    0.36
     Appearing
    0.35
    迷
    0.35
    ങ്ങനെ
    0.34
     Volt
    0.34
    ໌
    0.34
    POSITIVE LOGITS
     site
    1.77
    现场
    1.59
    site
    1.52
    現場
    1.45
    Site
    1.42
     Site
    1.40
     scene
    1.37
    SITE
    1.32
     sites
    1.31
     SITE
    1.30
    Activations Density 0.158%

    No Known Activations