© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 214371
    Prev
    Next
    INDEX
    Explanations

    liquids like milk, water, broth

    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
    %\
    0.39
     dropped
    0.39
    ミ
    0.38
    いに
    0.37
     extensively
    0.37
     ఏర్
    0.37
    руппа
    0.36
     prepare
    0.36
     '^
    0.36
     פּ
    0.36
    POSITIVE LOGITS
     broth
    0.46
     dần
    0.41
     bouillon
    0.40
     menambah
    0.40
     sipping
    0.39
     absorption
    0.39
     presidents
    0.38
    Facet
    0.38
    airplane
    0.38
    蒸汽
    0.38
    Activations Density 0.045%

    No Known Activations