© 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. 22-GEMMASCOPE-RES-131K
    7. 128738
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on unusually long (multisyllabic) words in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    specific descriptors

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     including
    -1.34
    包括
    -1.14
     has
    -1.11
     includes
    -1.10
     such
    -1.07
     alongside
    -1.02
     like
    -0.95
     by
    -0.93
     sees
    -0.93
     without
    -0.93
    POSITIVE LOGITS
    踯
    1.09
     Comprar
    1.08
     perché
    1.05
     ストラップ
    1.02
    throughout
    1.00
     noastră
    0.99
    chosen
    0.97
     ruh
    0.96
     serai
    0.96
     abonnement
    0.96
    Activations Density 0.048%

    No Known Activations