© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7097
    Prev
    Next
    INDEX
    Explanations

    Hydraulically actuated

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

    The neuron detects snippets of CMSSW Python configuration code (the “import FWCore.ParameterSet.Config as cms; process = cms.Process(…)” style .cff loading statements).

    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
    peach
    -0.87
    mbira
    -0.80
    octobre
    -0.78
    EXTERN
    -0.76
    chaussures
    -0.75
     löytyy
    -0.74
    Peach
    -0.74
     Exteriores
    -0.73
    しています
    -0.71
    subtle
    -0.71
    POSITIVE LOGITS
    process
    0.88
    廃
    0.85
    eneration
    0.84
    label
    0.81
    Parameter
    0.80
    )#
    0.80
     വ
    0.79
    TestBed
    0.79
    ourcing
    0.79
    ENABLE
    0.79
    Activations Density 0.003%

    No Known Activations