© 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. 2426
    Prev
    Next
    INDEX
    Explanations

    surface weather and speed analysis

    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
     attentes
    -0.82
     aument
    -0.81
     Cof
    -0.79
     Guilherme
    -0.78
    tivis
    -0.78
     动态
    -0.77
    BSC
    -0.77
     Arne
    -0.77
    quería
    -0.76
    inau
    -0.75
    POSITIVE LOGITS
     surface
    1.35
     Surface
    1.16
    Surface
    1.06
    surface
    1.04
     moisture
    0.94
    ionais
    0.93
     anomalies
    0.91
     Pr
    0.91
     SURFACE
    0.90
     curl
    0.81
    Activations Density 0.015%

    No Known Activations