© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 26677
    Prev
    Next
    INDEX
    Explanations

    retired or unemployed people

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

    The neuron flags words that describe personal life status changes or major life events (e.g. retirement, unemployment, moving, career shifts).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ⠻
    -0.91
    ὲν
    -0.84
    ρίες
    -0.82
     vecka
    -0.82
    ÇÕES
    -0.82
     appraise
    -0.82
     [''],
    -0.82
     Inorg
    -0.80
    filters
    -0.79
    ᆨ
    -0.79
    POSITIVE LOGITS
     unemployed
    1.00
     unemployment
    0.91
    dańsk
    0.89
    Then
    0.89
    ❱
    0.88
     leisurely
    0.88
     Then
    0.86
    ',(
    0.84
     Normalmente
    0.84
    人员
    0.82
    Activations Density 0.059%

    No Known Activations