© 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. 932
    Prev
    Next
    INDEX
    Explanations

    financial markets and trading

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    नलोड
    -2.42
     unangemessene
    -2.00
     market
    -1.95
    蚴
    -1.91
    媗
    -1.86
    ～！
    -1.85
    犇
    -1.85
    取り付け
    -1.84
    かもし
    -1.81
    勍
    -1.81
    POSITIVE LOGITS
     markets
    2.64
     are
    2.44
     If
    1.98
    但我
    1.94
    }{\
    1.87
    te
    1.84
    喾
    1.81
     But
    1.80
    )-
    1.78
     Aan
    1.77
    Activations Density 0.004%

    No Known Activations