© 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. 98070
    Prev
    Next
    INDEX
    Explanations

    performing actions

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

    The neuron is primarily activated by commas, i.e. it detects comma punctuation.

    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
     kysy
    -1.29
     DÍA
    -1.07
     információ
    -1.07
     permainan
    -1.05
     pemain
    -0.99
    lepší
    -0.98
     pertemuan
    -0.98
     myö
    -0.98
     được
    -0.97
     diccionario
    -0.97
    POSITIVE LOGITS
     deft
    1.12
     examined
    1.09
     absent
    1.05
     carefully
    1.02
     proceed
    0.98
     surveyed
    0.97
     proceeded
    0.94
     experimentally
    0.94
    开始了
    0.93
     minuten
    0.91
    Activations Density 0.014%

    No Known Activations