© 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. 65400
    Prev
    Next
    INDEX
    Explanations

    subjective perception and experience

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

    The neuron is strongly activated by formal scientific and clinical terminology—especially abstract nouns and verbs found in method or definition sections (e.g. “subjective,” “perceptions,” “investigate,” “mechanism”).

    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
    льевич
    -0.97
     valable
    -0.96
    respect
    -0.93
     condam
    -0.90
    knowing
    -0.88
     respecte
    -0.85
    パクト
    -0.85
    ürnberg
    -0.84
     garan
    -0.84
     obliga
    -0.84
    POSITIVE LOGITS
     perception
    4.78
     perceived
    4.75
    Perception
    3.75
    perception
    3.73
     perceptions
    3.64
     perceive
    3.58
     Perception
    3.53
     Perceived
    3.42
     percepción
    3.09
     perceives
    2.98
    Activations Density 0.165%

    No Known Activations