© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 23969
    Prev
    Next
    INDEX
    Explanations

    pour and pouring liquids

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

    verbs related to liquid transfer, particularly "pour" and variations of pouring.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     他
    -2.58
    ～。
    -2.55
     BRARY
    -2.52
     einzigartigen
    -2.48
     мой
    -2.42
     besonderen
    -2.39
     allgemeinen
    -2.34
    ሖ
    -2.31
     praktischen
    -2.31
     wesentlichen
    -2.25
    POSITIVE LOGITS
    </h3>
    2.64
    猡
    2.47
     POUR
    2.30
    喾
    2.28
    眼下
    2.28
    .’
    2.27
     célè
    2.25
    逦
    2.23
     wijn
    2.23
    亹
    2.22
    Activations Density 0.002%

    No Known Activations