© 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. 26589
    Prev
    Next
    INDEX
    Explanations

    Kaitaia Airport

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

    This neuron detects numeric tokens used in scholarly references (e.g. volume, issue, page, and year numbers in 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
     clinched
    -0.96
    etzung
    -0.95
    ६
    -0.91
     Eigentü
    -0.90
     banyo
    -0.90
    帘
    -0.89
     entdeckt
    -0.89
    ができます
    -0.87
     prestigious
    -0.87
     blending
    -0.85
    POSITIVE LOGITS
     ARTS
    1.13
    vaila
    1.10
    ніе
    1.09
     AGE
    1.01
    médi
    1.00
     indeed
    1.00
    毬
    0.99
     contextLoads
    0.98
     مباراة
    0.98
     comuniques
    0.98
    Activations Density 0.002%

    No Known Activations