© 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. 34-GEMMASCOPE-RES-131K
    4. 33044
    Prev
    Next
    INDEX
    Explanations

    highly positive adjectives

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

    The neuron responds most strongly to content‐bearing tokens—common nouns, pronouns, adjectives, etc.—i.e. words carrying the main topical or informational load 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
     ganska
    -0.94
    astanza
    -0.94
    tą
    -0.93
    ázquez
    -0.91
    convenient
    -0.90
     graag
    -0.83
     пусть
    -0.83
     bonitas
    -0.82
     sorella
    -0.82
    ActionBar
    -0.81
    POSITIVE LOGITS
     super
    1.70
     superb
    1.54
     simply
    1.41
     terrific
    1.32
     beyond
    1.30
     супер
    1.26
     fantastic
    1.23
     really
    1.20
     extraordinary
    1.19
     tremendous
    1.19
    Activations Density 0.017%

    No Known Activations