© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 3004
    Prev
    Next
    INDEX
    Explanations

    gut and digestion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_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
     skater
    0.80
     RTP
    0.80
     vamp
    0.78
     bina
    0.77
     skate
    0.76
    🧛
    0.75
     NBA
    0.75
    ⛸
    0.74
     skating
    0.73
    vertices
    0.73
    POSITIVE LOGITS
     digestive
    2.65
     intestinal
    2.52
     gastro
    2.42
     gut
    2.38
     Digestive
    2.35
     stomach
    2.33
     intestines
    2.26
     intestine
    2.19
     digestion
    2.16
     Gut
    2.16
    Activations Density 0.365%

    No Known Activations