© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38339
    Prev
    Next
    INDEX
    Explanations

    biblical figures taking flight or action

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

    The neuron fires strongly on mentions of individual people’s names or personal references (especially proper names).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    诡异
    -1.55
    但却
    -1.35
     demokra
    -1.33
    咂
    -1.31
     amd
    -1.30
    ㌘
    -1.29
    Моя
    -1.28
    からない
    -1.28
    十分的
    -1.27
    臃
    -1.26
    POSITIVE LOGITS
     after
    2.03
     his
    1.49
     during
    1.46
     before
    1.44
     волосся
    1.39
     made
    1.34
     gave
    1.28
     nine
    1.28
     he
    1.26
     using
    1.25
    Activations Density 0.023%

    No Known Activations