© 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. 34-GEMMASCOPE-RES-131K
    7. 78014
    Prev
    Next
    INDEX
    Explanations

    heap and parent relationships

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

    The neuron strongly activates on numeric tokens (digits and counts) in algorithm-style or code contexts.

    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
    ktes
    -0.82
     setError
    -0.82
    Angels
    -0.81
     KISS
    -0.79
    Superman
    -0.79
    tillation
    -0.78
     Cholesterol
    -0.77
    aver
    -0.77
    Stade
    -0.77
     Hick
    -0.76
    POSITIVE LOGITS
     heap
    1.34
    heap
    1.11
    Heap
    1.00
     father
    0.95
     parent
    0.94
     Heap
    0.87
     subtree
    0.86
     swim
    0.86
     parents
    0.85
     sink
    0.84
    Activations Density 0.006%

    No Known Activations