© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130642
    Prev
    Next
    INDEX
    Explanations

    descriptive adjective followed by noun

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

    The neuron fires on strong evaluative adjectives and adverbs (often promotional or high-degree descriptors, e.g. “stunning,” “cost-effective,” “advanced,” “friendly”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    étiques
    -1.80
     clínicas
    -1.74
     wyłą
    -1.67
     seleccionadas
    -1.65
     fået
    -1.60
    葑
    -1.59
    calça
    -1.58
     afectadas
    -1.58
    anwalt
    -1.57
     colecciones
    -1.56
    POSITIVE LOGITS
     amount
    2.11
     answer
    2.06
     approach
    2.00
     attempt
    1.99
     way
    1.95
     example
    1.95
     effect
    1.82
     method
    1.79
     result
    1.78
     extent
    1.76
    Activations Density 0.261%

    No Known Activations