© 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. 101719
    Prev
    Next
    INDEX
    Explanations

    names and proper nouns

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

    This neuron activates on occurrences of React PropTypes (i.e. the identifier “PropTypes” and its uses in prop‐type definitions).

    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
    躂
    -2.89
     This
    -2.88
    镠
    -2.53
    d
    -2.45
    i
    -2.42
     attorno
    -2.22
     halt
    -2.17
    晅
    -2.14
    Semua
    -2.13
    holms
    -2.13
    POSITIVE LOGITS
    を選
    2.67
    部分が
    2.66
     でも
    2.66
    僦
    2.61
    狨
    2.61
    橚
    2.56
    玊
    2.55
    部分を
    2.53
     eases
    2.48
    紺
    2.42
    Activations Density 0.002%

    No Known Activations