© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81518
    Prev
    Next
    INDEX
    Explanations

    plus one

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

    The neuron is detecting the “+” addition operator in code and math expressions.

    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
     only
    -1.19
     even
    -1.05
     eight
    -0.99
     four
    -0.98
    اهر
    -0.94
     fifty
    -0.94
    酒屋
    -0.93
     some
    -0.92
     six
    -0.90
     because
    -0.90
    POSITIVE LOGITS
    ledem
    1.03
     ۱
    0.98
    に変
    0.90
    nels
    0.84
     طلب
    0.80
     predetermin
    0.80
    Osp
    0.80
    юра
    0.78
     abur
    0.77
    ENBERG
    0.77
    Activations Density 0.005%

    No Known Activations