© 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. 33839
    Prev
    Next
    INDEX
    Explanations

    colors and styles

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

    The neuron fires strongly on multiword commercial product or brand names (e.g. nail polishes, cosmetics, beers, plant cultivars).

    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
    Zaj
    -1.09
     decorativo
    -1.05
     zodiaco
    -1.01
     superbes
    -1.00
     borracha
    -0.99
    icei
    -0.97
    Mål
    -0.97
    ovým
    -0.96
     inventario
    -0.95
     великолеп
    -0.94
    POSITIVE LOGITS
    $
    0.99
    </em>
    0.97
     &
    0.95
    //
    0.91
    start
    0.91
     to
    0.90
    filter
    0.88
    tide
    0.88
    </
    0.87
    depth
    0.87
    Activations Density 0.036%

    No Known Activations