© 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. 2202
    Prev
    Next
    INDEX
    Explanations

    concept or notion

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

    The neuron specializes in spotting high-level academic/conceptual keywords (e.g. notion, concept, theory, properties) commonly used to introduce or frame ideas in scholarly writing.

    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
    рои
    -0.90
    र्क
    -0.81
    κολ
    -0.77
    เหตุ
    -0.77
    视着
    -0.76
    スマス
    -0.75
     PROTOCOL
    -0.75
    🐤
    -0.74
    politik
    -0.73
    Caf
    -0.73
    POSITIVE LOGITS
     concept
    6.25
     concepts
    5.44
     notion
    5.25
    concept
    5.00
     concepto
    4.69
     notions
    4.44
    Concept
    4.34
    概念
    4.31
     Concept
    4.22
    concepts
    4.06
    Activations Density 0.144%

    No Known Activations