© 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. 129849
    Prev
    Next
    INDEX
    Explanations

    The neuron responds to domain-specific technical keywords—especially configuration terms, file names, parameter/permission labels, and other specialized nouns in technical documentation.

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

    file and path configurations

    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
     biela
    -1.15
     wzglę
    -1.14
     fidèles
    -1.09
     monté
    -1.06
     てき
    -1.06
     zupeł
    -0.98
    jednoc
    -0.97
    Regret
    -0.94
     vérit
    -0.94
     répondit
    -0.94
    POSITIVE LOGITS
     femenina
    0.93
     Bemerkungen
    0.88
     dyr
    0.88
    parken
    0.86
    lenia
    0.86
     makeStyles
    0.85
    рка
    0.85
     hlm
    0.84
     ہیں۔
    0.84
     tą
    0.84
    Activations Density 0.044%

    No Known Activations