© 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. 34-GEMMASCOPE-RES-131K
    7. 2249
    Prev
    Next
    INDEX
    Explanations

    so I can / so you can / so we can

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

    The neuron responds to first‐ and second‐person pronouns (I, you, we) and associated modal helpers (can, would) used in instructional or self-referential contexts.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     however
    -1.20
     probably
    -1.00
     đâu
    -0.96
     costuma
    -0.95
    сього
    -0.95
    ())).
    -0.93
     provavelmente
    -0.91
     usually
    -0.90
     often
    -0.90
     havia
    -0.90
    POSITIVE LOGITS
     don
    1.80
     doesn
    1.77
     can
    1.53
    不要
    1.27
     بتوان
    1.25
    不会
    1.24
     not
    1.14
     ikke
    1.14
     didn
    1.13
     doesnt
    1.13
    Activations Density 0.036%

    No Known Activations