© 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. 5308
    Prev
    Next
    INDEX
    Explanations

    plasma and high temperatures

    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
     Indoor
    0.48
    вя
    0.45
     Denmark
    0.44
    皖
    0.44
     ANOVA
    0.43
     Türkiye
    0.43
    沺
    0.43
    俆
    0.43
    祯
    0.42
    між
    0.41
    POSITIVE LOGITS
     plasma
    0.95
     plasmas
    0.93
    plasma
    0.84
     thermonuclear
    0.82
    Plasma
    0.80
     PLASMA
    0.71
     Plasma
    0.71
     ignited
    0.67
     chromosphere
    0.67
    PLASMA
    0.66
    Activations Density 0.212%

    No Known Activations