© 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. 16061
    Prev
    Next
    INDEX
    Explanations

    loan, rent, disorder, SDR, Sr

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

    The neuron activates on content-bearing tokens—nouns, verbs, adjectives, and acronyms—i.e. non-stopwords rather than 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
     todella
    -0.88
     spørs
    -0.87
     inevitably
    -0.87
     giebt
    -0.86
     suivez
    -0.85
     ведет
    -0.84
     revealed
    -0.84
     stát
    -0.82
    イッチ
    -0.82
     prominently
    -0.81
    POSITIVE LOGITS
    各種
    1.02
    葡
    1.00
    atario
    0.98
    although
    0.97
    ismic
    0.96
     Giro
    0.96
     baik
    0.96
     senator
    0.95
     Chu
    0.94
    nemers
    0.94
    Activations Density 0.049%

    No Known Activations