© 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. 34-GEMMASCOPE-RES-131K
    7. 93310
    Prev
    Next
    INDEX
    Explanations

    making and manufacturing

    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
    Bred
    -0.96
     Francus
    -0.87
    艉
    -0.86
     Utilization
    -0.84
    uai
    -0.83
     สาว
    -0.83
    ینی
    -0.83
     frische
    -0.82
    艏
    -0.82
    开来
    -0.81
    POSITIVE LOGITS
     maker
    2.89
     creation
    2.56
    maker
    2.50
     makers
    2.47
    making
    2.25
     production
    2.17
     making
    2.11
     Maker
    2.08
    makers
    2.06
    Maker
    2.03
    Activations Density 0.171%

    No Known Activations