© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15551
    Prev
    Next
    INDEX
    Explanations

    and [name]

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

    This neuron detects bibliographic reference tokens—author names, years, and numerical citation markers common in academic citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     comunit
    -1.28
     desglose
    -1.05
    
    -1.01
     flexibel
    -0.98
    нимание
    -0.98
    RouterModule
    -0.97
    tigheter
    -0.96
    CommonModule
    -0.95
     verifica
    -0.95
    凭借
    -0.95
    POSITIVE LOGITS
     others
    2.03
     subsequent
    1.63
     later
    1.62
     many
    1.57
     other
    1.49
     our
    1.45
     повече
    1.30
     especially
    1.27
     more
    1.14
     bahkan
    1.14
    Activations Density 0.040%

    No Known Activations