© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109288
    Prev
    Next
    INDEX
    Explanations

    retirement planning and savings

    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
    SError
    -0.90
    取出
    -0.80
     valer
    -0.79
    の人は
    -0.79
    タブレット
    -0.78
    '].'
    -0.78
     Ramadan
    -0.75
    mpä
    -0.75
     fupp
    -0.75
     đăng
    -0.75
    POSITIVE LOGITS
     preparedness
    1.09
     planning
    1.04
     savings
    1.02
     proceedings
    1.00
     preparation
    0.96
     plans
    0.92
     prediction
    0.91
     preparación
    0.90
    PARTY
    0.88
     presents
    0.88
    Activations Density 0.023%

    No Known Activations