© 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. 130756
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on first‐person self-references, i.e. tokens like “I,” “my,” and other personal commentary markers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    "I" followed by personal action or feeling

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     slutet
    -1.11
     at
    -1.05
    DAD
    -1.00
    过来了
    -0.98
     augusti
    -0.96
    ijk
    -0.95
    iseks
    -0.94
    扱
    -0.94
     terbesar
    -0.94
     unique
    -0.93
    POSITIVE LOGITS
    respective
    1.22
     astuces
    1.17
    Watching
    1.16
    事が
    1.15
     stratég
    1.13
     personally
    1.09
     Watching
    1.07
     neither
    1.07
     myself
    1.05
    𓆏
    1.03
    Activations Density 0.052%

    No Known Activations