© 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. 22-GEMMASCOPE-RES-131K
    7. 130786
    Prev
    Next
    INDEX
    Explanations

    This neuron strongly detects byline and editorial credit terms—especially the word “Editor” (and its variants) in headers and author/credit lines.

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

    editor:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    ’
    -3.13
    "
    -2.75
     incluindo
    -2.31
     They
    -2.27
    s
    -2.25
     بالإضافة
    -2.25
    e
    -2.16
    borderSide
    -2.14
    on
    -2.09
    老年
    -2.09
    POSITIVE LOGITS
    狆
    2.84
    猡
    2.52
    貲
    2.23
    城的
    2.20
    𝕻
    2.19
    鶲
    2.19
     защиту
    2.17
    ୈ
    2.17
     diesem
    2.16
    揷
    2.16
    Activations Density 0.013%

    No Known Activations