© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13653
    Prev
    Next
    INDEX
    Explanations

    inflammatory and anti-inflammatory

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

    indirect effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efficiency
    0.45
     い
    0.45
     கற்று
    0.43
     പിന്നെ
    0.43
     efficiency
    0.42
     учеб
    0.42
    elia
    0.42
     मेथड
    0.41
    旮
    0.40
     गेम
    0.39
    POSITIVE LOGITS
     proinflammatory
    0.81
     inflammatory
    0.68
     inflam
    0.67
     cytokine
    0.66
    TNF
    0.66
     cytokines
    0.61
    inflammatory
    0.56
     TNF
    0.56
     comorbid
    0.56
     Infl
    0.55
    Activations Density 0.200%

    No Known Activations