© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81726
    Prev
    Next
    INDEX
    Explanations

    Berg and Borg names

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

    The neuron activates on names or words containing the substring “berg” (or the closely related “borg”) in proper nouns.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     datab
    -0.91
     OPTIONAL
    -0.77
     Charg
    -0.77
     admiral
    -0.76
     MacOS
    -0.76
     SHOCK
    -0.75
     Ecc
    -0.75
     JAVA
    -0.75
     Spruce
    -0.75
     ariel
    -0.75
    POSITIVE LOGITS
    mann
    0.82
     Berg
    0.80
     small
    0.80
     contemporáneo
    0.79
     comedy
    0.75
     Scherer
    0.75
     cervical
    0.74
    ила
    0.74
     viagra
    0.73
     th
    0.73
    Activations Density 0.025%

    No Known Activations