© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 58831
    Prev
    Next
    INDEX
    Explanations

    support

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

    The neuron detects mentions of support, i.e. words like “support,” “supportive,” or “supports.”

    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
     what
    -1.80
     new
    -1.73
     How
    -1.73
     Since
    -1.70
     So
    -1.66
     Because
    -1.65
     avoid
    -1.64
     And
    -1.61
     There
    -1.60
     What
    -1.59
    POSITIVE LOGITS
     groote
    1.63
    鹩
    1.62
    鶿
    1.59
     každé
    1.52
     bré
    1.51
     geene
    1.51
     ſur
    1.50
    蔸
    1.50
    tifs
    1.48
    鱨
    1.48
    Activations Density 0.028%

    No Known Activations