© 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. 99095
    Prev
    Next
    INDEX
    Explanations

    buying or opting

    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
    unread
    -0.78
     BIOLOGY
    -0.71
     presump
    -0.70
    īs
    -0.68
     подчер
    -0.66
    isEnd
    -0.66
    经验
    -0.65
     Zusammenhang
    -0.65
     glory
    -0.65
    Brazil
    -0.65
    POSITIVE LOGITS
     buy
    3.38
    buy
    2.61
     Buy
    2.56
    Buy
    2.38
     buys
    2.09
     buying
    1.99
    买
    1.97
     BUY
    1.93
    BUY
    1.88
     bought
    1.85
    Activations Density 0.017%

    No Known Activations