© 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. 34-GEMMASCOPE-RES-131K
    7. 38246
    Prev
    Next
    INDEX
    Explanations

    asset management firms

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

    The neuron reliably detects corporate‐style investment management and financial institution terminology—especially formal company names and boilerplate around “Investment,” “Management,” and related brand identifiers.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     EXPEND
    -0.75
    urals
    -0.75
    Pozdrawiam
    -0.73
     transi
    -0.71
     McColl
    -0.71
     cag
    -0.70
     Gadgets
    -0.70
    銃
    -0.70
     Bosco
    -0.69
     bing
    -0.69
    POSITIVE LOGITS
     asset
    1.40
     manager
    1.38
     Asset
    1.29
     managers
    1.20
    Asset
    1.16
     management
    1.01
    asset
    1.00
    manager
    1.00
    Managers
    0.99
     Managers
    0.98
    Activations Density 0.034%

    No Known Activations