© 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. 50454
    Prev
    Next
    INDEX
    Explanations

    high strength alloy steels

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

    The neuron is specialized in spotting numeric- and alphanumeric‐heavy technical specifications (e.g. material grades, dimensions, voltages) embedded in the text.

    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
    berkeley
    -0.73
    mercury
    -0.72
     founded
    -0.69
    次回
    -0.69
    ार
    -0.69
     几
    -0.69
    meria
    -0.68
     transparence
    -0.68
     almoço
    -0.68
    Mercury
    -0.68
    POSITIVE LOGITS
     steels
    1.52
     steel
    1.13
     strength
    1.08
     grade
    1.05
     grades
    0.97
     Grade
    0.83
    钢
    0.81
     Grades
    0.80
     Strength
    0.77
    Strength
    0.73
    Activations Density 0.019%

    No Known Activations