© 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. 10-GEMMASCOPE-RES-131K
    4. 124040
    Prev
    Next
    INDEX
    Explanations

    disc, rotor, brake, cylinder, pads

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

    The neuron detects technical mentions of brake system components (e.g. pads, rotors, drums, cylinders, lathes) in an automotive or mechanical context.

    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
    几分
    -1.50
     
    -1.41
    s
    -1.41
    v
    -1.38
    k
    -1.32
    x
    -1.30
     it
    -1.28
     things
    -1.27
     toalha
    -1.26
    ↵↵
    -1.25
    POSITIVE LOGITS
    ’,
    1.52
     们
    1.48
    esterol
    1.44
    Since
    1.44
    </>
    
    1.42
    ۠
    1.41
    __":
    
    1.39
    푉
    1.37
    ponential
    1.36
     reemplazo
    1.35
    Activations Density 0.027%

    No Known Activations