© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30440
    Prev
    Next
    INDEX
    Explanations

    wetting and contact angle phenomena

    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
    ריס
    -0.87
    今年も
    -0.80
    ніе
    -0.80
    וכ
    -0.79
     Dilution
    -0.77
     dwellings
    -0.76
     propeller
    -0.74
    𝓴
    -0.73
     Ears
    -0.72
     drifts
    -0.72
    POSITIVE LOGITS
     wetting
    1.46
     spreading
    1.19
     Cassie
    1.17
    wet
    1.13
     contact
    1.09
     wet
    1.07
     Wilhel
    1.05
     advancing
    0.99
    Wet
    0.98
    Cassie
    0.98
    Activations Density 0.106%

    No Known Activations