© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105827
    Prev
    Next
    INDEX
    Explanations

    interactive applications or experiences

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

    The neuron fires on occurrences of the word “interactive.”

    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
    ↵
    -2.48
     The
    -2.45
     decidedly
    -2.38
    犼
    -2.34
     to
    -2.25
     intrepid
    -2.19
     VERY
    -2.16
    cadeau
    -2.13
    馓
    -2.11
    ↵↵
    -2.09
    POSITIVE LOGITS
    After
    3.50
    Even
    3.39
    Following
    3.30
    While
    3.30
    Despite
    3.28
    Unlike
    3.28
    Several
    3.27
    During
    3.25
    One
    3.19
    Because
    3.17
    Activations Density 0.003%

    No Known Activations