© 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. 127818
    Prev
    Next
    INDEX
    Explanations

    The neuron responds specifically to first-person singular self-references, i.e. occurrences of “I” marking personal statements.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    "I" statements and actions

    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
    Negative Logits
    ↵↵↵↵
    -1.16
     seit
    -1.13
    /,
    -1.12
     erforderlich
    -1.09
    .*;
    -1.06
     ziekte
    -1.06
    since
    -1.05
    ਊ
    -1.05
     mostr
    -1.03
    ↵↵↵↵↵↵↵
    -1.02
    POSITIVE LOGITS
     my
    1.23
     ἐ
    1.11
     becomes
    1.09
     more
    1.07
    ınca
    1.06
     during
    1.05
     anew
    1.03
     ὑ
    1.02
    SUND
    1.02
     when
    1.01
    Activations Density 0.028%

    No Known Activations