© 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. 58289
    Prev
    Next
    INDEX
    Explanations

    code blocks

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

    The neuron strongly activates on comparison operators (==, !=) and default empty‐value literals (0, "", nil), so it’s detecting emptiness/zero‐value checks 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
    ).
    -2.30
    )
    -2.05
    .)
    -1.92
    )
    -1.73
    )=
    -1.59
    ?)
    -1.46
    ),
    -1.45
     '')
    -1.41
    ())
    -1.38
    )</
    -1.34
    POSITIVE LOGITS
     {
    1.88
     then
    1.73
     {
    1.63
     thì
    1.61
    <h3>
    1.47
     {
    1.22
    "){
    1.20
     ]];
    1.20
     sitten
    1.11
    (){
    1.09
    Activations Density 0.010%

    No Known Activations