© 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. 64366
    Prev
    Next
    INDEX
    Explanations

    departure or death

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

    The neuron flags tokens that describe major life‐ or career‐events or state changes (e.g. crashes, resignations, deaths, moves).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     навіть
    -1.45
    即便
    -1.25
     even
    -1.24
     nawet
    -1.23
    即使
    -1.20
     حتی
    -1.09
     даже
    -1.05
     même
    -1.01
     chiar
    -0.97
    despite
    -0.97
    POSITIVE LOGITS
    ėd
    0.91
    🤬
    0.90
    🐍
    0.89
    ncbi
    0.88
     경우
    0.87
    árt
    0.86
    pilih
    0.85
     RIVER
    0.83
    weiter
    0.83
    👽
    0.83
    Activations Density 0.030%

    No Known Activations