© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71890
    Prev
    Next
    INDEX
    Explanations

    code elements and data structures

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

    This neuron detects numeric coordinate values (multi-digit numbers) in technical wiring or block‐layout descriptions.

    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
     récup
    -0.94
     perca
    -0.88
     russo
    -0.88
     sebel
    -0.86
     kado
    -0.84
    lerim
    -0.84
    EventLoop
    -0.84
    akteur
    -0.83
    olio
    -0.83
     PREMI
    -0.82
    POSITIVE LOGITS
    不应该
    0.85
    Compra
    0.84
    ૮
    0.82
     möjlighet
    0.77
     Slay
    0.77
    ADA
    0.77
    ena
    0.77
    
    0.75
    sslich
    0.74
    satis
    0.74
    Activations Density 0.031%

    No Known Activations