© 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. 104686
    Prev
    Next
    INDEX
    Explanations

    assets under management or allocation

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

    The neuron is detecting occurrences of the word “asset.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    references to assets and related financial/legal concepts, especially in investment and management contexts.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "asset" or "assets" in financial and legal contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered 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
    ."
    -1.65
    .”
    -1.40
    .“
    -1.38
     mélange
    -1.30
     rues
    -1.29
     mélang
    -1.29
     epithet
    -1.27
     arrang
    -1.26
    没有了
    -1.25
    ')))
    -1.24
    POSITIVE LOGITS
    这里
    1.43
     bedingt
    1.41
     debe
    1.38
    1.37
    其他
    1.35
     assets
    1.35
    辛い
    1.35
     griechischen
    1.35
     schwed
    1.32
     &
    1.31
    Activations Density 0.020%

    No Known Activations