© 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. 4318
    Prev
    Next
    INDEX
    Explanations

    REST templates and queries

    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
     jerawat
    -0.74
     biryani
    -0.71
    补充
    -0.68
     imagines
    -0.68
    льная
    -0.67
    Mmmm
    -0.67
    يري
    -0.66
    થ
    -0.66
    idl
    -0.66
     构造
    -0.66
    POSITIVE LOGITS
    Template
    1.16
    Support
    1.13
    template
    1.12
     template
    1.11
     support
    1.09
     Support
    1.04
     Template
    1.04
    getTemplate
    0.96
    support
    0.94
    upport
    0.89
    Activations Density 0.071%

    No Known Activations