© 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. 70963
    Prev
    Next
    INDEX
    Explanations

    functionality and features

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

    The neuron is keyed to spotting the word “support” (and its minor misspellings) in the text.

    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
    人文
    -1.49
     actually
    -1.47
    晚餐
    -1.41
     ostensibly
    -1.40
     because
    -1.39
     étan
    -1.38
     this
    -1.37
    卓越
    -1.35
     some
    -1.33
    ཫ
    -1.33
    POSITIVE LOGITS
    敺
    1.68
    灕
    1.65
     możliwość
    1.55
    蔔
    1.55
    一丝
    1.54
    ivores
    1.52
    uated
    1.52
    ”).
    1.50
     folgendes
    1.44
     และ
    1.43
    Activations Density 0.030%

    No Known Activations