© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 72731
    Prev
    Next
    INDEX
    Explanations

    standard library imports

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

    The neuron fires on dotted API or library calls—that is, sequence of identifier-period-identifier patterns.

    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
     since
    -1.58
    :%.
    -1.46
     sejak
    -1.35
    地在
    -1.35
    unno
    -1.34
    !");
    
    -1.30
     komunikasi
    -1.27
     simbol
    -1.27
     didalam
    -1.26
     radioButton
    -1.26
    POSITIVE LOGITS
     your
    1.72
     it
    1.70
          
    1.41
     you
    1.40
                          
    1.37
                 
    1.35
     etc
    1.34
    miyorum
    1.33
                       
    1.30
     habrían
    1.29
    Activations Density 0.355%

    No Known Activations