© 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. 98607
    Prev
    Next
    INDEX
    Explanations

    machines, machinery, equipment

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

    The neuron specializes in spotting structured form‐field labels or machine specification fields (e.g. “Machine type,” “Machine number,” “Surname,” etc.).

    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
    Wholesale
    -0.91
     wholesale
    -0.80
    生まれる
    -0.77
     Toxicol
    -0.73
    𝟎
    -0.72
     Wholesale
    -0.71
     Lord
    -0.70
     Konkurrenz
    -0.70
    getDriver
    -0.70
     Preisen
    -0.69
    POSITIVE LOGITS
     machines
    1.95
     machine
    1.81
     machinery
    1.74
     equipment
    1.74
     Machines
    1.53
     Machine
    1.45
    machine
    1.43
    机器
    1.40
    Machine
    1.38
    machines
    1.38
    Activations Density 0.055%

    No Known Activations