© 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. 34-GEMMASCOPE-RES-131K
    7. 107946
    Prev
    Next
    INDEX
    Explanations

    digital marketing and advertising

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

    The neuron fires on digital‐marketing jargon and buzzwords (e.g. “SEO,” “social media,” “content marketing,” “webinars,” etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     typeName
    -0.90
     gewiß
    -0.83
     deß
    -0.80
     vín
    -0.80
    esha
    -0.79
     sangue
    -0.79
    ifikationen
    -0.79
    .《
    -0.78
    INP
    -0.76
     Motherboard
    -0.76
    POSITIVE LOGITS
     email
    2.25
     paid
    1.79
    email
    1.78
     Email
    1.78
     social
    1.77
    Email
    1.62
     Paid
    1.54
     SEO
    1.46
     EMAIL
    1.42
     PPC
    1.42
    Activations Density 0.038%

    No Known Activations