© 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. 39795
    Prev
    Next
    INDEX
    Explanations

    stages of development

    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
     každé
    -1.05
    每個
    -0.95
     каждой
    -0.91
     привлека
    -0.89
    Earlier
    -0.88
    の一覧
    -0.88
    After
    -0.87
    after
    -0.86
    ziehung
    -0.84
     каждый
    -0.83
    POSITIVE LOGITS
     preliminary
    1.13
     partial
    1.12
    初步
    1.10
     tentative
    1.05
     полови
    0.96
    liminary
    0.95
     önemli
    0.95
    partial
    0.94
     complete
    0.91
     inconclusive
    0.91
    Activations Density 0.068%

    No Known Activations