© 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. 113118
    Prev
    Next
    INDEX
    Explanations

    sewage, redux, prowess

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

    The neuron is highly sensitive to occurrences of the word “sewage” (often in contexts like “sewage sludge” or sewage treatment).

    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
    0
    -3.97
    section
    -2.83
    e
    -2.78
    l
    -2.78
     {
    -2.70
    u
    -2.45
    ed
    -2.36
    z
    -2.20
    en
    -2.20
    <i>
    -2.20
    POSITIVE LOGITS
    ☫
    2.58
     graduación
    2.47
     \_
    2.42
    
    2.36
     cúp
    2.36
    𝛥
    2.34
    %;
    2.34
    ſſen
    2.33
    龊
    2.33
    
    2.31
    Activations Density 0.007%

    No Known Activations