© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 98207
    Prev
    Next
    INDEX
    Explanations

    boolean false

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

    The neuron activates strongly on numeric literals (numbers) in 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
     yes
    -1.13
    Yes
    -0.99
     one
    -0.88
     indeed
    -0.88
     Yes
    -0.86
     daya
    -0.83
    大于
    -0.80
     oui
    -0.79
     satu
    -0.74
    assertTrue
    -0.73
    POSITIVE LOGITS
     false
    3.05
    false
    2.48
     False
    2.25
     FALSE
    2.02
    FALSE
    1.95
    False
    1.87
    assertFalse
    1.78
     falsehood
    1.66
     falso
    1.56
     nope
    1.55
    Activations Density 0.019%

    No Known Activations