© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7139
    Prev
    Next
    INDEX
    Explanations

    gases and their properties

    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_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
    extrait
    0.48
    种子
    0.47
    肾
    0.47
    鐲
    0.47
    狨
    0.46
    遗产
    0.46
    жу
    0.45
    apsingToolbar
    0.45
    槭
    0.45
    夺
    0.44
    POSITIVE LOGITS
     gas
    1.59
     gases
    1.54
     gás
    1.35
    gas
    1.29
     gaseous
    1.28
     Gas
    1.27
     methane
    1.24
     गैस
    1.17
    Gas
    1.17
     propane
    1.17
    Activations Density 0.200%

    No Known Activations