© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43376
    Prev
    Next
    INDEX
    Explanations

    tears and related bodily fluids

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

    references to tears, tear ducts, or tear production in both medical and emotional contexts.

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

    The neuron lights up on any mention of tears or tear‐related terms (e.g. “tear,” “tears,” “tear film,” “teardrops,” 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_10/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
     Also
    -2.11
     Some
    -2.09
    >
    -1.98
     use
    -1.97
     There
    -1.91
     has
    -1.89
    Some
    -1.89
     Several
    -1.89
    しないと
    -1.88
     need
    -1.87
    POSITIVE LOGITS
    臜
    2.06
     vijf
    2.03
     realizando
    1.85
     miniaturka
    1.85
    selbe
    1.84
    鴬
    1.80
    wakili
    1.77
     comienzan
    1.74
     hauptsächlich
    1.73
    GridColumn
    1.72
    Activations Density 0.008%

    No Known Activations