© 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. 91968
    Prev
    Next
    INDEX
    Explanations

    something made

    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
     料理
    -0.85
    Varint
    -0.82
    を開催
    -0.79
    Developed
    -0.79
    пса
    -0.78
    hasClass
    -0.77
    lai
    -0.76
    鸷
    -0.75
     Khar
    -0.75
    worked
    -0.75
    POSITIVE LOGITS
     made
    5.72
    made
    3.63
    Made
    3.45
     make
    3.23
     Made
    3.09
     making
    3.06
     gemaakt
    2.88
     gemacht
    2.83
     сделан
    2.64
    MADE
    2.61
    Activations Density 0.130%

    No Known Activations