© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127804
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on tokens that serve as field‐ or parameter‐names (e.g. keys in JSON/XML/Make/LDAP/CSS snippets).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    LOCAL_MODULE, PACKAGE, NAME, TYPE

    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
    Negative Logits
     rozgry
    -1.07
     waaronder
    -1.04
     élector
    -0.97
     MARSHALL
    -0.93
     rajut
    -0.93
     része
    -0.91
    corrhi
    -0.91
     ALFRED
    -0.88
     argentino
    -0.88
    回合
    -0.88
    POSITIVE LOGITS
     grammi
    0.94
     ingredienti
    0.84
    Hawai
    0.83
    Fabricante
    0.82
    laş
    0.81
    byteArray
    0.77
    NewUrl
    0.76
     indicato
    0.76
    ཞ
    0.75
     Еще
    0.75
    Activations Density 0.003%

    No Known Activations