© 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. 10-GEMMASCOPE-RES-131K
    7. 101381
    Prev
    Next
    INDEX
    Explanations

    intuitive and instinctive understanding

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

    The neuron activates on occurrences of “intuitive” (and closely related variants like “intuition” or “instinctive”).

    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
    ritsar
    -1.75
    螓
    -1.73
    ámide
    -1.65
    actéristi
    -1.63
     esteemed
    -1.59
     în
    -1.53
    旆
    -1.52
     cárcel
    -1.50
    鉨
    -1.48
     sogenannten
    -1.47
    POSITIVE LOGITS
    ଽ
    1.47
    ❡
    1.38
    くちゃ
    1.38
     rằng
    1.36
    $
    1.33
    挖掘
    1.31
    pagnols
    1.31
     Instinct
    1.29
     getName
    1.26
    زة
    1.26
    Activations Density 0.008%

    No Known Activations