© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8417
    Prev
    Next
    INDEX
    Explanations

    news articles or headlines

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

    The neuron detects tokens containing the consecutive letters “jal.”

    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
    焿
    -2.75
    之类的
    -2.61
    筈
    -2.59
     Пі
    -2.50
     contemporánea
    -2.36
     compartida
    -2.34
     következő
    -2.34
    鋮
    -2.30
    thansa
    -2.30
    
    -2.25
    POSITIVE LOGITS
    "
    3.13
    䜣
    2.66
    ?"
    2.38
     "'
    2.30
    锨
    2.28
     "
    2.25
     =
    2.20
    ⸩
    2.16
    
    2.09
    
    2.08
    Activations Density 0.001%

    No Known Activations