© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 112863
    Prev
    Next
    INDEX
    Explanations

    mercury and Hg combinations

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

    mentions of mercury and related chemical compounds.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     raiſ
    -2.66
    1
    -2.41
    “
    -2.39
    _
    -2.38
    2
    -2.22
    .'
    -2.19
     véritable
    -2.14
    как
    -2.13
    5
    -2.13
     deſt
    -2.11
    POSITIVE LOGITS
    蔼
    2.14
    ρών
    2.05
     撮っ
    2.05
    蒞
    2.05
    蕯
    2.02
    KommentareTeilen
    2.00
    кторов
    1.98
    𖥧
    1.93
     Füßen
    1.92
     theres
    1.89
    Activations Density 0.009%

    No Known Activations