© 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. 1955
    Prev
    Next
    INDEX
    Explanations

    names after comma

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

    The neuron is keyed to punctuation and other sentence‐boundary markers (periods, commas, apostrophes, etc.).

    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
    ándolos
    -1.05
    Доброго
    -0.91
     Armageddon
    -0.91
    Leírás
    -0.90
     disputa
    -0.89
     оско
    -0.89
    лкой
    -0.88
    山市
    -0.88
     stond
    -0.88
    жает
    -0.87
    POSITIVE LOGITS
     android
    1.10
    nologia
    0.97
     perciò
    0.94
    cuencia
    0.93
    pañol
    0.90
    món
    0.88
     oameni
    0.88
     Agents
    0.88
     き
    0.88
    athion
    0.87
    Activations Density 0.106%

    No Known Activations