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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118901
    Prev
    Next
    INDEX
    Explanations

    numerical weather prediction

    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
    洙
    -0.80
    notNull
    -0.75
     sáng
    -0.71
     crimp
    -0.70
     Olu
    -0.69
    дры
    -0.68
     Hø
    -0.68
    üht
    -0.68
    ennai
    -0.66
     glyco
    -0.66
    POSITIVE LOGITS
    schemes
    0.96
     prognostic
    0.92
     Boug
    0.89
    Forecast
    0.88
     SCHEME
    0.87
     schemes
    0.85
     forecast
    0.84
     Kain
    0.83
     prepare
    0.82
    bld
    0.82
    Activations Density 0.011%

    No Known Activations