© 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. 79870
    Prev
    Next
    INDEX
    Explanations

    dates and court circuits

    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
    balleur
    -1.04
    これだけ
    -1.03
     nostre
    -1.02
     печени
    -1.01
    ६
    -1.00
    esség
    -0.95
    */
    -0.95
    较为
    -0.93
    르
    -0.93
    ticum
    -0.90
    POSITIVE LOGITS
     government
    1.33
     authorities
    1.28
    ַּ
    1.13
     officials
    1.09
     management
    1.09
    ִּ
    1.06
     principle
    1.03
     Government
    1.02
     executive
    1.02
     both
    0.96
    Activations Density 0.040%

    No Known Activations