© 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. 83849
    Prev
    Next
    INDEX
    Explanations

    market share and percentages

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

    The neuron flags words and phrases that denote corporate performance metrics or business‐growth figures (e.g. market share, sales, losses, tripling, percentages).

    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
    enseur
    -0.83
     FetchType
    -0.82
    ꒳
    -0.78
    Semif
    -0.75
    ]&
    -0.73
     AttributeSet
    -0.73
    ynchronous
    -0.73
    ৱ
    -0.72
     Anlage
    -0.72
    anden
    -0.71
    POSITIVE LOGITS
     market
    4.06
     share
    3.75
    share
    2.88
    market
    2.83
    Share
    2.81
     shares
    2.78
    Market
    2.70
    シェア
    2.67
     Share
    2.59
     Market
    2.48
    Activations Density 0.029%

    No Known Activations