© 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. 48039
    Prev
    Next
    INDEX
    Explanations

    moisture and wetness

    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
    uko
    -0.76
    Sunlight
    -0.75
     خارجية
    -0.75
     purify
    -0.74
    Rigidbody
    -0.73
     Sunlight
    -0.71
    UKO
    -0.68
     המק
    -0.67
     Sediment
    -0.67
     очистки
    -0.67
    POSITIVE LOGITS
     wet
    4.69
     moist
    3.66
    wet
    3.64
    Wet
    3.47
     Wet
    3.39
     damp
    3.16
     moisture
    3.00
     WET
    2.91
    WET
    2.89
     wetter
    2.75
    Activations Density 0.080%

    No Known Activations