© 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. 15723
    Prev
    Next
    INDEX
    Explanations

    question Answering

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

    This neuron primarily detects numeric tokens—especially citation indices, section/figure numbers, and other in-text reference numbers.

    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
     autobús
    -0.98
     lele
    -0.94
     mikina
    -0.93
     eſt
    -0.92
    myfile
    -0.92
    uuuuu
    -0.91
     avión
    -0.91
    nnn
    -0.91
    -.-
    -0.90
    cede
    -0.89
    POSITIVE LOGITS
     cilvē
    1.01
    पुर
    1.01
     Gläub
    0.94
    жном
    0.92
     sinistra
    0.88
    ttet
    0.88
    irchen
    0.87
     Như
    0.86
    我们
    0.85
     פאר
    0.85
    Activations Density 0.002%

    No Known Activations