© 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. 75006
    Prev
    Next
    INDEX
    Explanations

    water

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

    This neuron detects references to water and liquid substances, including their interactions with other materials or their presence in systems.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron specializes in spotting numeric tokens and measurements (numbers, decimals, and related numeric values).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     de
    -1.38
    6
    -1.33
    他的
    -1.32
    in
    -1.32
    henswürdigkeiten
    -1.31
    4
    -1.28
     некоторые
    -1.27
    7
    -1.27
     своей
    -1.23
     الثالث
    -1.20
    POSITIVE LOGITS
    的头
    1.55
    ⚢
    1.41
     PÅ
    1.41
    water
    1.38
     ストラップ
    1.28
     durata
    1.27
    tät
    1.26
    趼
    1.26
     網
    1.26
    網站
    1.25
    Activations Density 0.334%

    No Known Activations