Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8266
    Prev
    Next
    INDEX
    Explanations

    retirement and health plans

    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
     รา
    -0.78
    dependent
    -0.69
     تركيا
    -0.68
     kufanya
    -0.67
    リード
    -0.67
     utaf
    -0.66
     bisogno
    -0.66
    DRM
    -0.65
     しょう
    -0.65
     summer
    -0.65
    POSITIVE LOGITS
     plan
    1.53
     plans
    1.52
    plan
    1.22
     Plan
    1.13
     scheme
    1.10
    Plans
    1.08
     schemes
    1.08
    plans
    1.06
     PLAN
    1.02
     sponsors
    1.00
    Activations Density 0.034%

    No Known Activations