© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 66110
    Prev
    Next
    INDEX
    Explanations

    followed by punctuation or connector

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

    The neuron fires on semantically rich, multi-syllabic content words (especially nouns and descriptive adjectives) rather than on common function words.

    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
     joli
    -1.27
     concerne
    -1.23
     Planeta
    -1.23
     inva
    -1.23
     marchand
    -1.22
     oub
    -1.21
     erfaren
    -1.21
     Lettres
    -1.20
     dommage
    -1.18
    “……”
    -1.16
    POSITIVE LOGITS
     and
    2.39
     to
    2.30
     which
    1.95
     etc
    1.75
     as
    1.64
     or
    1.52
     of
    1.44
     so
    1.38
     ,
    1.29
     who
    1.26
    Activations Density 0.128%

    No Known Activations