© 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. 39783
    Prev
    Next
    INDEX
    Explanations

    advertising and marketing

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

    The neuron fires strongly on marketing and promotional copy—words commonly used in advertising or sales pitches.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    教学
    -1.23
     Uniwersyte
    -1.22
    tiously
    -1.20
     tortura
    -1.15
    eapples
    -1.10
     sendok
    -1.09
    Veja
    -1.08
     accelerated
    -1.06
     волосся
    -1.06
    шений
    -1.05
    POSITIVE LOGITS
     your
    1.62
     marketing
    1.38
    ﻷ
    1.30
     logos
    1.25
     logo
    1.21
     their
    1.21
     branding
    1.21
     фаса
    1.20
     APPELLANT
    1.20
     advertising
    1.19
    Activations Density 0.040%

    No Known Activations