© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 129691
    Prev
    Next
    INDEX
    Explanations

    The neuron highlights major content-bearing nouns and noun-like terms (key topic words) in the text.

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

    production cycle

    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
     Fußballspieler
    -1.06
    Zulu
    -0.97
     aldea
    -0.95
     Kills
    -0.95
    깅
    -0.93
    retim
    -0.91
     adi
    -0.91
    事です
    -0.91
     möglicherweise
    -0.91
    还得
    -0.91
    POSITIVE LOGITS
     and
    1.16
     blom
    0.98
     pengar
    0.95
     accessoires
    0.90
    8
    0.88
    因为
    0.86
     Jør
    0.85
    就是
    0.85
     susun
    0.83
     himmel
    0.82
    Activations Density 0.174%

    No Known Activations