© 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. 10-GEMMASCOPE-RES-131K
    7. 41557
    Prev
    Next
    INDEX
    Explanations

    constructor or class definitions

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

    The neuron responds to floating‐point number literals (numbers containing a decimal point) in code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     (!__
    -1.58
     such
    -1.45
     kenal
    -1.43
     recens
    -1.42
     incendie
    -1.41
     oubli
    -1.39
     annet
    -1.38
     dangere
    -1.38
     puissant
    -1.35
    ()?.
    -1.34
    POSITIVE LOGITS
     
    1.67
        
    1.55
            
    1.50
     также
    1.48
     has
    1.40
    rschein
    1.33
                
    1.32
    讴
    1.30
     zamiast
    1.27
          
    1.24
    Activations Density 0.014%

    No Known Activations