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. 8075
    Prev
    Next
    INDEX
    Explanations

    weather modification

    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
     poaching
    -0.83
    Coding
    -0.82
    Extensions
    -0.81
    utveck
    -0.81
     Trends
    -0.78
    erobic
    -0.77
    Cite
    -0.77
     إيران
    -0.75
    scanner
    -0.75
     Ep
    -0.75
    POSITIVE LOGITS
     cloud
    1.12
     spraying
    1.05
     weather
    1.02
     clouds
    1.00
    cloud
    0.99
     seeding
    0.91
     SRM
    0.91
     spray
    0.89
    spray
    0.89
     geo
    0.88
    Activations Density 0.015%

    No Known Activations