© 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. 10-GEMMASCOPE-RES-131K
    7. 119802
    Prev
    Next
    INDEX
    Explanations

    moisture and humidity levels

    np_acts-logits-general · gemini-2.5-flash-lite

    words and phrases related to moisture, dampness, and vapor.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    .”
    -1.83
    as
    -1.72
    of
    -1.70
    in
    -1.70
    also
    -1.59
     of
    -1.48
     that
    -1.41
    ของ
    -1.41
    v
    -1.38
     también
    -1.37
    POSITIVE LOGITS
     techniczne
    1.72
    珝
    1.51
    ampilan
    1.45
    ﺅ
    1.43
    嫱
    1.43
     debemos
    1.42
    issantes
    1.42
     humidity
    1.41
    Humidity
    1.41
    ௗ
    1.41
    Activations Density 0.052%

    No Known Activations