© 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. 34-GEMMASCOPE-RES-131K
    7. 31694
    Prev
    Next
    INDEX
    Explanations

    their pension

    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_34/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
    นน
    -0.77
    维持
    -0.76
    фро
    -0.75
    今年は
    -0.75
    Törté
    -0.73
     Fik
    -0.73
    鋅
    -0.72
     Hache
    -0.72
     mă
    -0.71
     unge
    -0.71
    POSITIVE LOGITS
     retirement
    3.08
     pension
    2.94
     Retirement
    2.19
    pension
    2.19
    retirement
    2.16
    Retirement
    2.14
     pensions
    2.09
     Pension
    2.06
    Pension
    1.88
     savings
    1.82
    Activations Density 0.039%

    No Known Activations