© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 41682
    Prev
    Next
    INDEX
    Explanations

    substances and their state or flow

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

    words referring to fluids or gases (like liquid, water, air, gas, fluid) in technical descriptions.

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

    The neuron fires on terms naming or describing flowable substances (liquid, fluid, gas, water, air) or their flow contexts.

    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
     également
    -1.61
     marital
    -1.40
     viata
    -1.30
     tiež
    -1.29
     diseñ
    -1.26
    tionnaire
    -1.25
     gastronomía
    -1.24
     хороший
    -1.24
     a
    -1.23
    ソード
    -1.22
    POSITIVE LOGITS
     to
    1.90
     that
    1.72
     "}";
    1.44
     into
    1.43
     from
    1.43
     about
    1.36
    dirond
    1.34
    használ
    1.25
     out
    1.23
     proveniente
    1.23
    Activations Density 0.190%

    No Known Activations