© 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. 129814
    Prev
    Next
    INDEX
    Explanations

    This neuron fires strongly on configuration or directive keywords and parameter names (often in ALL-CAPS or CamelCase) and their assigned values in code or config files.

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

    autosomal recessive, vertical, update, true

    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
    omorphic
    -1.17
    форма
    -0.97
     potom
    -0.89
     effektiv
    -0.87
    chenden
    -0.85
     anhänger
    -0.84
     tragé
    -0.84
    不愿
    -0.84
     drž
    -0.83
     Acesso
    -0.82
    POSITIVE LOGITS
     thankfully
    0.83
    ových
    0.82
    足以
    0.81
     پنجم
    0.81
     य
    0.77
     Customers
    0.75
    向前
    0.75
    即是
    0.74
     demnach
    0.73
     prosegu
    0.73
    Activations Density 0.043%

    No Known Activations