© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69039
    Prev
    Next
    INDEX
    Explanations

    behalf of

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

    The neuron detects tokens associated with formal representation, especially the phrase “on behalf of.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     kilom
    -1.60
    ＇
    -1.51
     »)
    -1.51
     TECHNIQUES
    -1.42
     «<
    -1.41
    IBLIO
    -1.38
    fion
    -1.36
     thuy
    -1.34
     |]
    -1.34
    ^'
    -1.34
    POSITIVE LOGITS
     These
    1.70
    0
    1.50
     Your
    1.48
     Aside
    1.45
     Some
    1.45
     There
    1.45
     Often
    1.43
     Despite
    1.41
     Almost
    1.41
     You
    1.40
    Activations Density 0.141%

    No Known Activations