© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25183
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    The neuron is triggered by numeric literals (standalone 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_22/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
     you
    -1.09
    tlement
    -1.08
    〉
    -1.02
    efits
    -1.01
    australia
    -0.99
     &
    -0.98
     estadounidense
    -0.98
     MemoryStream
    -0.98
     corrientes
    -0.98
    룬
    -0.97
    POSITIVE LOGITS
     aimez
    1.05
     cedera
    1.03
     行き
    1.02
    ESTY
    0.98
    によっては
    0.94
    どうも
    0.93
    Răsp
    0.92
    Then
    0.91
    grimas
    0.88
     班
    0.88
    Activations Density 0.002%

    No Known Activations