© 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. 34-GEMMASCOPE-RES-131K
    7. 823
    Prev
    Next
    INDEX
    Explanations

    accessing object properties or methods

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

    The neuron is triggered by numeric literals (tokens consisting of digits) in the 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_34/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
     in
    -1.05
     on
    -0.93
    Every
    -0.91
    Some
    -0.90
     aware
    -0.90
     Tän
    -0.87
     so
    -0.85
    DebuggerStep
    -0.81
     not
    -0.81
    śnie
    -0.80
    POSITIVE LOGITS
    悻
    1.03
    tissa
    0.99
     penultimate
    0.98
     +
    0.98
    NINGS
    0.97
     hinauf
    0.96
     gänzlich
    0.94
    基于
    0.94
    ville
    0.94
    𝐸
    0.92
    Activations Density 0.007%

    No Known Activations