© 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. 113097
    Prev
    Next
    INDEX
    Explanations

    drains sewage pipes

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

    words related to drainage systems, including drains, sewers, and water flow.

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

    The neuron strongly activates on words referring to drainage and sewer infrastructure (e.g. drain, storm, sewer, runoff).

    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
     its
    -1.66
    </b>
    -1.45
    èces
    -1.33
    看他
    -1.33
    standing
    -1.30
     "}";
    -1.29
    re
    -1.28
    g
    -1.28
    f
    -1.27
     estranho
    -1.27
    POSITIVE LOGITS
    vestidos
    1.23
     Personalis
    1.23
     ?
    1.22
    меч
    1.20
    Each
    1.18
     Each
    1.17
     vídeos
    1.14
    Fuckin
    1.13
    ཫ
    1.12
    kadang
    1.11
    Activations Density 0.042%

    No Known Activations