© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 98987
    Prev
    Next
    INDEX
    Explanations

    if then logic

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

    The neuron fires on numeric literals (numbers) in the text.

    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
     Unused
    -0.93
    りましたが
    -0.90
    Strut
    -0.89
     menatap
    -0.89
    SEVEN
    -0.88
     GSH
    -0.88
    IMENTS
    -0.87
    繆
    -0.86
     consultato
    -0.84
     pazar
    -0.84
    POSITIVE LOGITS
     if
    2.78
     then
    2.16
    if
    2.00
    如果
    1.99
     если
    1.94
     case
    1.77
    If
    1.77
     If
    1.69
     значит
    1.63
     means
    1.59
    Activations Density 0.011%

    No Known Activations