© 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. 2063
    Prev
    Next
    INDEX
    Explanations

    high quality or performance

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

    This neuron detects superlative or intensifying adjectives and adverbs (e.g. “high,” “superior,” “most,” “ultra,” “fast”) used to hype product quality.

    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
    ectomy
    -0.96
    があるので
    -0.90
    に行ってきました
    -0.88
    housing
    -0.88
    onBlur
    -0.82
    ׳
    -0.82
    BIÉN
    -0.81
    ableness
    -0.81
     bảo
    -0.80
    がありますが
    -0.80
    POSITIVE LOGITS
     efficiency
    0.97
     capacity
    0.96
     performance
    0.93
     resilience
    0.93
    兀
    0.93
     Capacity
    0.90
     quality
    0.84
     strength
    0.82
     torque
    0.82
    覺
    0.81
    Activations Density 0.048%

    No Known Activations