© 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. 10-GEMMASCOPE-RES-131K
    7. 112733
    Prev
    Next
    INDEX
    Explanations

    fecal matter and excretion

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

    references to fecal matter or stool in medical and scientific contexts.

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

    The neuron strongly activates on occurrences of the word “fecal” (i.e. references to fecal matter).

    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
    他们是
    -2.77
    怍
    -2.61
    身边的
    -2.52
     akin
    -2.39
    迨
    -2.39
    ，，
    -2.38
     instala
    -2.36
     observado
    -2.34
    髎
    -2.33
     entendido
    -2.23
    POSITIVE LOGITS
    2
    3.64
    6
    3.55
    7
    3.47
    9
    3.06
    4
    2.95
    l
    2.80
    5
    2.78
    e
    2.67
    on
    2.67
    3
    2.66
    Activations Density 0.003%

    No Known Activations