© 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. 10-GEMMASCOPE-RES-131K
    7. 75545
    Prev
    Next
    INDEX
    Explanations

    make a selection or request

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

    The neuron fires on words that denote actions or events—especially gerunds (-ing forms) and nominalizations ending in “-ion.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ]
    -1.73
    ння
    -1.54
     antics
    -1.42
     което
    -1.42
     tendremos
    -1.41
    viale
    -1.41
     которого
    -1.40
     portátiles
    -1.39
    พาะ
    -1.38
    icioso
    -1.38
    POSITIVE LOGITS
     in
    2.27
     about
    1.99
     on
    1.66
     based
    1.43
     insisted
    1.37
    阅读原文
    1.35
     situação
    1.32
    ใหญ
    1.32
     noches
    1.30
    以上です
    1.30
    Activations Density 0.054%

    No Known Activations