© 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-262K
    7. 136240
    Prev
    Next
    INDEX
    Explanations

    sulfur and chemical compounds

    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_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
     Confusion
    0.47
    󠁣
    0.43
     confusion
    0.42
    OHN
    0.40
     prerog
    0.40
    崞
    0.40
    ನ್ನ
    0.40
     மர
    0.39
     Qualification
    0.39
    divid
    0.38
    POSITIVE LOGITS
     sulfur
    1.83
     Sulfur
    1.67
     sulphur
    1.56
    Sulf
    1.52
    硫
    1.44
     sulfide
    1.38
     Sulph
    1.38
     sulfides
    1.38
    sulf
    1.32
     Sulf
    1.32
    Activations Density 0.023%

    No Known Activations