© 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. 17082
    Prev
    Next
    INDEX
    Explanations

    element mercury and planet mercury

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

    mercury and its health hazards

    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
     मंडल
    0.48
     جمله
    0.47
     deseo
    0.45
    adle
    0.44
    崗
    0.44
    ativamente
    0.44
    撩
    0.44
    డే
    0.43
    髌
    0.43
     आईपीएल
    0.42
    POSITIVE LOGITS
     Mercury
    0.83
    Mercury
    0.80
     mercury
    0.78
     Mercur
    0.74
     Hg
    0.71
     mercur
    0.65
    Hg
    0.61
     Merlin
    0.60
     Mer
    0.57
     mer
    0.56
    Activations Density 0.022%

    No Known Activations