© 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. 59173
    Prev
    Next
    INDEX
    Explanations

    audience types and demographics

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

    The neuron fires on high–information content words—especially topical nouns, verbs, and adjectives that carry the main news or descriptive meaning of a sentence.

    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
     laterale
    -1.04
     autonomia
    -0.98
     wrestlers
    -0.94
     木製
    -0.91
     miniatura
    -0.90
    🧍
    -0.88
    AUTHORS
    -0.87
     contestants
    -0.87
     قرن
    -0.85
    你有
    -0.84
    POSITIVE LOGITS
     casual
    1.98
     demographics
    1.60
     demographic
    1.56
     younger
    1.49
    casual
    1.43
     hardcore
    1.35
     Casual
    1.33
     mainstream
    1.30
    demographic
    1.19
     older
    1.18
    Activations Density 0.050%

    No Known Activations