© 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. 22-GEMMASCOPE-RES-131K
    7. 35890
    Prev
    Next
    INDEX
    Explanations

    free, A, B, failure, fan, semifinal

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

    This neuron detects domain-specific, content-bearing nouns or terms (e.g. specialized classifications, technical components, chemical names, medical conditions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     sportowe
    -1.05
     сына
    -0.99
     felf
    -0.99
     zim
    -0.96
     факты
    -0.96
     disfru
    -0.94
     chicas
    -0.94
    County
    -0.93
     вона
    -0.93
    有效
    -0.92
    POSITIVE LOGITS
    5
    1.09
     bakgrund
    1.09
    تحميل
    1.05
     detergents
    1.02
     sedan
    1.01
    perrt
    1.00
     iceberg
    0.99
    ametric
    0.99
     joggers
    0.99
     conseguenze
    0.99
    Activations Density 0.133%

    No Known Activations