© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59198
    Prev
    Next
    INDEX
    Explanations

    financial performance and metrics

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

    This neuron detects financial performance terms and metrics (e.g., cash flow, EBITDA, KPIs, profitability figures) and related executive labels (such as CFO).

    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
    </h1>
    -2.13
    9
    -2.11
    ᠂
    -2.05
     necessità
    -1.88
    ;.
    -1.88
    目前的
    -1.85
    4
    -1.83
     食事
    -1.79
     ロゴ
    -1.79
     variedad
    -1.79
    POSITIVE LOGITS
     
    2.19
    </em>
    1.86
     &
    1.77
     maravilh
    1.57
     is
    1.55
     crun
    1.50
    拮
    1.48
     für
    1.46
     дав
    1.43
     extraordinaria
    1.41
    Activations Density 0.002%

    No Known Activations