© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128867
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on general business-oriented prose—especially marketing/advertising and corporate-tech jargon—while ignoring more narrative or named-entity text.

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

    states of business

    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
     hongos
    -1.58
     muros
    -1.56
     especias
    -1.51
     motocicletas
    -1.51
    características
    -1.49
     cuarzo
    -1.48
    varios
    -1.46
     sés
    -1.45
     although
    -1.45
    囯
    -1.44
    POSITIVE LOGITS
    ૉ
    1.63
    :
    1.52
     data
    1.41
    “
    1.35
    сятся
    1.34
     end
    1.34
     vektör
    1.32
    etí
    1.30
     Data
    1.28
     industry
    1.28
    Activations Density 0.100%

    No Known Activations