© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 103699
    Prev
    Next
    INDEX
    Explanations

    solubility and dissolving

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

    dissolving in water

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     помо
    0.42
    циона
    0.41
    Contains
    0.40
    知道
    0.40
    োর্ড
    0.40
     стандарта
    0.40
    鲮
    0.40
     дете
    0.39
    зна
    0.39
    ана
    0.38
    POSITIVE LOGITS
     solub
    0.51
     dissol
    0.48
     facilidad
    0.46
     aç
    0.45
    cohol
    0.43
     atrav
    0.43
     parle
    0.43
     itu
    0.42
     dissolve
    0.42
    ว
    0.41
    Activations Density 0.010%

    No Known Activations