© 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. 10-GEMMASCOPE-RES-131K
    7. 119621
    Prev
    Next
    INDEX
    Explanations

    stainless steel fasteners

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

    The neuron is attuned to the word “fastener” (and its plural “fasteners”), strongly activating whenever that term appears.

    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
    ᥬ
    -2.42
    皛
    -2.23
    各样的
    -2.22
    étation
    -2.13
    ?"
    -2.09
    
    -2.05
    瓛
    -2.03
    ссор
    -1.95
    囖
    -1.91
    Jereo
    -1.91
    POSITIVE LOGITS
     they
    3.05
    as
    2.73
    $
    2.59
    k
    2.56
    to
    2.53
    ’
    2.50
    x
    2.47
    or
    2.47
    ta
    2.34
    s
    2.28
    Activations Density 0.001%

    No Known Activations