© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64395
    Prev
    Next
    INDEX
    Explanations

    will see

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

    The neuron mainly activates on capitalized tokens—i.e. proper names, brands, model names, and other words beginning with an uppercase letter.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     many
    -1.30
    amblea
    -0.98
    vodu
    -0.95
     by
    -0.94
     Because
    -0.87
     toreb
    -0.86
     różne
    -0.84
    ۈ
    -0.84
    文化
    -0.84
    Many
    -0.84
    POSITIVE LOGITS
    enseignements
    1.02
     will
    1.02
     fyra
    0.99
     bäst
    0.98
     meanwhile
    0.98
    楫
    0.96
     tohto
    0.96
    れたら
    0.95
     restantes
    0.95
    车的
    0.95
    Activations Density 0.021%

    No Known Activations