© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 90082
    Prev
    Next
    INDEX
    Explanations

    medical and testing procedures

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

    technical or procedural descriptions in scientific, medical, or engineering texts.

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

    The neuron strongly activates on technical descriptions of industrial fire‐protection or piping systems—especially passages detailing “wet‐pipe” sprinkler setups and their routine maintenance procedures (e.g. draining, refilling, and returning the system to operation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    Boxscore
    -0.84
    ?><
    -0.81
    rosz
    -0.80
     Gartner
    -0.79
     Greta
    -0.79
     новогод
    -0.77
     Relay
    -0.75
    RSC
    -0.75
     Yam
    -0.75
     parlant
    -0.75
    POSITIVE LOGITS
     testing
    2.00
     test
    1.99
     hydrostatic
    1.81
     tested
    1.58
     Testing
    1.55
     hydro
    1.54
     tests
    1.49
    testing
    1.34
     Test
    1.33
    hydro
    1.30
    Activations Density 0.040%

    No Known Activations