© 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. 107831
    Prev
    Next
    INDEX
    Explanations

    Appellate Court

    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
     故
    -0.72
     COUNTY
    -0.70
     abolish
    -0.69
    })=\
    -0.68
     multip
    -0.68
    üglich
    -0.67
    gencias
    -0.67
     reprezenta
    -0.67
     Argus
    -0.67
    wpa
    -0.66
    POSITIVE LOGITS
     Kawasaki
    0.79
     Lingu
    0.73
     Chao
    0.72
     saya
    0.72
     Commissioner
    0.72
     Linguistics
    0.71
     composting
    0.70
     lingü
    0.70
    haria
    0.70
     Sig
    0.70
    Activations Density 0.048%

    No Known Activations