© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 11208
    Prev
    Next
    INDEX
    Explanations

    moisture and dampness

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

    humidity and moisture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    боли
    0.48
    turb
    0.45
    閻
    0.44
     bolstering
    0.42
     stirred
    0.42
    垡
    0.42
    InsertInt
    0.41
    罾
    0.41
    蒡
    0.41
     народного
    0.40
    POSITIVE LOGITS
     moisture
    2.41
     Moisture
    2.36
     wet
    2.19
    湿
    2.14
     moist
    2.09
     humidity
    2.05
     Wet
    2.02
     humedad
    1.99
    Wet
    1.99
    濕
    1.98
    Activations Density 0.643%

    No Known Activations