© 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. 58260
    Prev
    Next
    INDEX
    Explanations

    posters as art or retail items

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

    The neuron strongly activates on occurrences of the word “poster” (in any form or capitalization).

    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
     tämä
    -0.92
    Scul
    -0.87
     treachery
    -0.86
     vzduchu
    -0.85
     erhöht
    -0.85
     pursuance
    -0.85
     corrientes
    -0.85
    watering
    -0.82
     festive
    -0.82
     生日
    -0.82
    POSITIVE LOGITS
    childNodes
    1.04
     campaign
    0.95
    arrayList
    0.93
    サイズ
    0.92
    </h3>
    0.92
    ized
    0.91
    Campaign
    0.91
    azzi
    0.90
     EconPapers
    0.87
     contesta
    0.86
    Activations Density 0.010%

    No Known Activations