© 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. 68297
    Prev
    Next
    INDEX
    Explanations

    classification, measurement, outcomes

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

    The neuron activates on key domain-specific technical or scientific content words (e.g. major topic nouns and terms) in a document.

    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
    श
    -1.05
     --
    -1.04
    　　
    -1.03
     bezahlt
    -1.03
     εδώ
    -1.01
     ţ
    -1.00
                          
    -0.99
    со
    -0.99
                      
    -0.98
                   
    -0.98
    POSITIVE LOGITS
    Поэтому
    1.12
     حتی
    1.11
    邂
    1.02
    modèle
    1.00
     tasarım
    0.98
    jusqu
    0.97
     навіть
    0.95
     invertir
    0.94
     nawet
    0.92
    donc
    0.92
    Activations Density 0.273%

    No Known Activations