© 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. 10-GEMMASCOPE-RES-131K
    7. 43004
    Prev
    Next
    INDEX
    Explanations

    on behalf of

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

    This neuron detects instances of representation phrasing, specifically the “on behalf of” construction.

    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
    '
    -2.97
     
    -2.78
    .
    -2.55
     '
    -2.28
     is
    -2.11
    "
    -2.08
      
    -1.95
    が入
    -1.90
     argued
    -1.80
     $
    -1.78
    POSITIVE LOGITS
    ﱠ
    2.28
    烀
    2.17
     our
    2.16
    ቍ
    2.14
     gustado
    2.13
    卺
    2.05
    Специ
    2.02
    ляции
    1.98
     અને
    1.97
    cinogenicity
    1.93
    Activations Density 0.007%

    No Known Activations