© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34915
    Prev
    Next
    INDEX
    Explanations

    have been

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

    The neuron is keyed to personal and demonstrative pronouns (e.g. “I,” “it,” “you,” “there”) and related forms of “to be” (e.g. “am,” “is,” “has”).

    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
     nike
    -1.07
    nitř
    -0.95
     itinéraire
    -0.93
    茈
    -0.92
     десер
    -0.91
     deluded
    -0.91
    ᱚ
    -0.91
     emirates
    -0.91
     incompet
    -0.90
     municip
    -0.89
    POSITIVE LOGITS
     siang
    1.03
     πριν
    1.02
     recently
    1.00
     gearbeitet
    0.98
     sayuran
    0.93
     ladr
    0.92
     possibilities
    0.92
     creato
    0.89
     tayang
    0.88
     biji
    0.88
    Activations Density 0.354%

    No Known Activations