© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64185
    Prev
    Next
    INDEX
    Explanations

    gastric, gastrointestinal, gastropod

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

    The neuron detects variations of the word "gastric" and related terms like "gastropod," particularly at the beginning of medical and biological texts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is detecting occurrences of the root “gast–” (as in gastric, gastro-, gastropods, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fixed
    -0.91
     Fixed
    -0.90
    نے
    -0.88
     FIXED
    -0.85
    fixed
    -0.85
    spur
    -0.84
     FIX
    -0.82
    Fixed
    -0.81
     lern
    -0.79
     固定
    -0.78
    POSITIVE LOGITS
     Gast
    1.13
     gast
    1.10
    intestinal
    1.09
    Gast
    1.04
     intestinal
    0.95
    gast
    0.93
     gastro
    0.85
     Lu
    0.82
     Julia
    0.81
    нял
    0.81
    Activations Density 0.026%

    No Known Activations