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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 58730
    Prev
    Next
    INDEX
    Explanations

    relative humidity

    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
    ICZ
    -0.76
     лест
    -0.75
     venomous
    -0.75
     yell
    -0.74
     Price
    -0.72
    auc
    -0.72
    的价格
    -0.71
     yells
    -0.71
     proprement
    -0.71
     venom
    -0.71
    POSITIVE LOGITS
     humidity
    4.09
     relative
    3.22
     RH
    2.97
     Relative
    2.94
     Humidity
    2.92
    Relative
    2.83
    humidity
    2.77
    relative
    2.72
    Humidity
    2.70
    RH
    2.61
    Activations Density 0.038%

    No Known Activations