© 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. 58794
    Prev
    Next
    INDEX
    Explanations

    else if conditional

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

    The neuron fires on code-branching “else” clauses.

    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
     ELSE
    -1.05
     Else
    -0.99
     Ganzen
    -0.99
    Результат
    -0.98
     líqu
    -0.94
     SURE
    -0.94
    cibo
    -0.94
    かなかった
    -0.92
     STAY
    -0.91
    mment
    -0.91
    POSITIVE LOGITS
     if
    1.87
     also
    1.68
     też
    1.02
     גם
    0.92
    Also
    0.91
    cl
    0.90
    {
    0.89
    ni
    0.88
    ta
    0.87
    ก็
    0.85
    Activations Density 0.003%

    No Known Activations