© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 17082
    Prev
    Next
    INDEX
    Explanations

    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-it/resid_post/layer_31_width_262k_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
     جمله
    0.45
    he
    0.42
    ativamente
    0.41
    髌
    0.41
     만족
    0.41
     جانتے
    0.40
    nese
    0.38
     영
    0.38
     জ্ঞ
    0.38
    emoration
    0.38
    POSITIVE LOGITS
     Mercury
    0.80
     mercury
    0.76
    Mercury
    0.76
     Mercur
    0.67
     Hg
    0.67
     mercur
    0.59
    汞
    0.57
     Mer
    0.53
    Hg
    0.52
     mercure
    0.51
    Activations Density 0.026%

    No Known Activations