© 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. 87386
    Prev
    Next
    INDEX
    Explanations

    electrical wire

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

    The neuron fires on occurrences of the standalone token “wire” (in any context, e.g. “Business Wire,” code modules named Wire, Market wire, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    mentions of the wire root, especially in technical/library names and in newswire contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "WIRE" or "Wire" in technical, business, or code contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
     
    -2.84
     —
    -2.17
     ebenso
    -2.16
    Our
    -2.14
    Let
    -2.13
    About
    -2.13
    AN
    -2.13
    ’
    -2.11
    $
    -2.06
    だけでなく
    -2.05
    POSITIVE LOGITS
    ו
    2.64
    u
    2.61
    änemark
    2.52
    鲼
    2.47
    âce
    2.44
    MENT
    2.39
    闢
    2.34
     pérd
    2.34
    e
    2.31
    izzera
    2.30
    Activations Density 0.006%

    No Known Activations