© 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. 66658
    Prev
    Next
    INDEX
    Explanations

    sewer and sewage systems

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

    references to sewer systems or sewage in text.

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

    The neuron strongly activates on words related to sewer or sewage systems (e.g. “sewer,” “sewers,” “sewage”).

    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
    艄
    -3.25
    ーズン
    -2.98
    튿
    -2.86
    僰
    -2.78
    
    -2.78
    苤
    -2.70
    ⚣
    -2.67
    訁
    -2.55
    臯
    -2.55
    genodigd
    -2.53
    POSITIVE LOGITS
     With
    2.61
     Since
    2.59
    觊
    2.56
     for
    2.52
     When
    2.45
    }$
    2.34
     Even
    2.34
     Despite
    2.34
     longstanding
    2.31
    на
    2.28
    Activations Density 0.004%

    No Known Activations