© 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. 93533
    Prev
    Next
    INDEX
    Explanations

    variable declarations with semicolons

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

    The neuron fires on literal constant tokens in code (e.g. numeric literals like “0” or “2” and the null literal).

    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
     then
    -1.34
    then
    -1.09
    Then
    -1.07
     if
    -1.03
    if
    -0.98
     obviously
    -0.95
    센
    -0.93
     clearly
    -0.87
    שְׁ
    -0.86
    orElseThrow
    -0.84
    POSITIVE LOGITS
     selalu
    1.07
    ieš
    1.03
     zawsze
    1.02
     всегда
    0.97
     pernah
    0.96
     băr
    0.94
     nigdy
    0.91
     pensó
    0.88
     vielmehr
    0.88
     هنا
    0.88
    Activations Density 0.024%

    No Known Activations