© 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. 1690
    Prev
    Next
    INDEX
    Explanations

    connectors and separators

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

    This neuron fires on terms that describe a system’s status or change—words signaling things being discontinued, in flux, subject to change, not working/open, needing modification, and so on.

    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
     erwor
    -1.54
    ῞
    -1.49
     verschied
    -1.45
     geprü
    -1.45
     strikingly
    -1.44
     pranzo
    -1.44
    涑
    -1.42
     ausgewä
    -1.41
     onore
    -1.38
     molte
    -1.38
    POSITIVE LOGITS
     in
    2.22
     provide
    1.56
     because
    1.53
     give
    1.53
     if
    1.51
    -
    1.47
     make
    1.43
     as
    1.42
     since
    1.40
     there
    1.39
    Activations Density 0.143%

    No Known Activations