© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10610
    Prev
    Next
    INDEX
    Explanations

    liquid

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

    viscosity and consistency of liquids

    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
     हवा
    0.48
    ancellor
    0.44
     हिंद
    0.43
     एयर
    0.42
     solitaire
    0.42
     ग्रैंड
    0.41
    翩
    0.41
    надцать
    0.41
     plucked
    0.40
     crumbling
    0.40
    POSITIVE LOGITS
     liquid
    1.65
    液
    1.59
    液体
    1.55
     Liquid
    1.54
     liquids
    1.52
    Liquid
    1.52
    liquid
    1.46
     liquide
    1.46
     Liquids
    1.46
     líquido
    1.37
    Activations Density 0.592%

    No Known Activations