© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31382
    Prev
    Next
    INDEX
    Explanations

    liquids and fluids

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dryness
    0.49
     干
    0.48
     transistors
    0.45
    石头
    0.43
     khô
    0.43
    ాల్
    0.42
     vouchers
    0.42
     сухо
    0.41
    嘏
    0.40
     خش
    0.39
    POSITIVE LOGITS
     liquids
    1.31
     liquid
    1.30
    液体
    1.20
    液
    1.20
     fluids
    1.14
     liquide
    1.12
     Liquids
    1.10
     líquido
    1.09
     fluid
    1.06
     жидкости
    1.05
    Activations Density 0.066%

    No Known Activations