© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64677
    Prev
    Next
    INDEX
    Explanations

    learning trades

    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_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
    miyorum
    -0.93
    在乎
    -0.80
    ↻
    -0.71
    gründet
    -0.71
    tipo
    -0.70
     Morgen
    -0.69
     annum
    -0.66
    forschung
    -0.66
     Machine
    -0.66
     רא
    -0.66
    POSITIVE LOGITS
     trades
    2.53
     trade
    2.50
    trade
    2.06
    trades
    1.84
    Trade
    1.79
     Trade
    1.66
    Trades
    1.65
     Trades
    1.55
    TRADE
    1.50
     traded
    1.36
    Activations Density 0.019%

    No Known Activations