© 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. 10-GEMMASCOPE-RES-131K
    7. 39964
    Prev
    Next
    INDEX
    Explanations

    PHP if statements

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

    The neuron triggers on numeric literal tokens in code (i.e. standalone numbers like 200, 13.5, 156, etc.).

    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
     same
    -2.47
    "
    -2.36
     next
    -2.34
     first
    -2.33
    {
    -2.30
     time
    -2.17
     most
    -2.14
    )
    -2.08
     last
    -2.06
    .
    -1.98
    POSITIVE LOGITS
    readFileSync
    2.05
    ⎆
    2.00
     spearheaded
    1.98
    ଃ
    1.96
    絝
    1.95
    fatalError
    1.94
     SUCH
    1.88
     kompatibel
    1.84
     apó
    1.84
     rastre
    1.84
    Activations Density 0.002%

    No Known Activations