© 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. 34-GEMMASCOPE-RES-131K
    7. 56063
    Prev
    Next
    INDEX
    Explanations

    knife, blade, cutting

    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
    vpc
    -0.77
    Thêm
    -0.73
     coef
    -0.72
    bandera
    -0.72
     fingerprint
    -0.71
    Principle
    -0.71
     DDT
    -0.69
     planting
    -0.69
     welding
    -0.68
     Nagoya
    -0.68
    POSITIVE LOGITS
     knife
    2.09
     blade
    1.78
     knives
    1.73
     blades
    1.55
     Knife
    1.44
    knife
    1.40
    刀
    1.39
     cutter
    1.38
     scissors
    1.34
     razor
    1.34
    Activations Density 0.033%

    No Known Activations