© 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. 34-GEMMASCOPE-RES-131K
    7. 23647
    Prev
    Next
    INDEX
    Explanations

    target reach consumers

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

    The neuron fires on tokens that signal the target or direction of marketing actions—words that introduce who or what the promotional message is “to.”

    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
     Applicant
    -0.91
     Applicants
    -0.89
     Beginners
    -0.88
    Applicant
    -0.85
     bivolt
    -0.85
    TestData
    -0.82
     sodio
    -0.82
    wiki
    -0.82
     olímp
    -0.81
    offensive
    -0.81
    POSITIVE LOGITS
     target
    2.14
     potential
    1.93
     customers
    1.65
    Potential
    1.62
    Target
    1.60
    target
    1.56
     prospects
    1.55
     potenciales
    1.51
     prospective
    1.46
     Target
    1.41
    Activations Density 0.026%

    No Known Activations