© 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. 22-GEMMASCOPE-RES-131K
    7. 12588
    Prev
    Next
    INDEX
    Explanations

    citations and identifiers

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

    This neuron activates on the numeric and punctuated elements of bibliographic citations—volume and issue numbers, years, page ranges, and DOIs—in academic references.

    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
     recurrir
    -1.06
     involucrados
    -1.04
     udaler
    -1.02
    SanPham
    -0.99
    signol
    -0.98
     vieron
    -0.98
     kupić
    -0.97
    wales
    -0.96
     Accesorios
    -0.96
    Ű
    -0.96
    POSITIVE LOGITS
     potes
    1.30
     Betrach
    1.04
     persiste
    1.01
     consumi
    1.01
     всегда
    0.98
    子が
    0.96
     cemento
    0.96
    そのため
    0.96
     puni
    0.96
    Hilfe
    0.95
    Activations Density 0.181%

    No Known Activations