© 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
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9097
    Prev
    Next
    INDEX
    Explanations

    kidney disease and renal conditions

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

    kidney and renal terms

    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_40_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
    企业的
    0.48
    Mast
    0.47
    企业
    0.47
    箫
    0.44
    铠
    0.44
    蓝牙
    0.43
     şark
    0.42
     Montgomery
    0.41
    Montgomery
    0.41
     calving
    0.40
    POSITIVE LOGITS
     kidney
    2.36
     renal
    2.31
    腎
    2.25
     neph
    2.23
     Renal
    2.16
     kidneys
    2.13
     Kidney
    2.09
     Neph
    2.06
    肾
    2.03
     किडनी
    1.95
    Activations Density 0.120%

    No Known Activations