© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130983
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on first‐person personal statements—especially “I/my” narrative content about one’s own plans, experiences, or life updates.

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

    college professor

    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
     with
    -1.38
     nė
    -1.20
     then
    -1.11
     using
    -1.10
     octavia
    -1.09
     would
    -1.09
     dieną
    -1.09
     lopez
    -1.04
     dortmund
    -1.02
     berikut
    -1.02
    POSITIVE LOGITS
     caminhão
    1.27
     sophomore
    1.26
     Isso
    1.25
     avião
    1.23
     tênis
    1.23
     college
    1.20
     Suède
    1.18
     Ostat
    1.18
     presque
    1.17
    rimi
    1.17
    Activations Density 0.114%

    No Known Activations