© 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. 22-GEMMASCOPE-RES-131K
    7. 67582
    Prev
    Next
    INDEX
    Explanations

    email addresses and names

    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_22/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
     foton
    -0.76
    ÍN
    -0.75
    itez
    -0.75
     мәкал
    -0.75
     télécommande
    -0.74
    ุม
    -0.73
     Boyer
    -0.73
    tät
    -0.72
    Personal
    -0.71
    Abra
    -0.71
    POSITIVE LOGITS
    ϲ
    0.95
     territ
    0.88
     Polícia
    0.84
    𝙑
    0.81
    घ
    0.81
     changed
    0.81
     mysterious
    0.81
     kebersihan
    0.80
     something
    0.80
    CDK
    0.80
    Activations Density 0.077%

    No Known Activations