© 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. 33150
    Prev
    Next
    INDEX
    Explanations

    academic, programming, and specific contexts

    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
    кога
    -0.85
     veel
    -0.85
    Résumé
    -0.84
     tył
    -0.79
    離開
    -0.78
    druid
    -0.77
    écou
    -0.77
    Tory
    -0.76
    Your
    -0.73
     Gem
    -0.73
    POSITIVE LOGITS
    leby
    0.86
    lared
    0.81
    endforeach
    0.81
    inii
    0.80
    atég
    0.80
    useState
    0.79
    ntz
    0.77
     Breakers
    0.76
    ńcz
    0.76
     Vertigo
    0.76
    Activations Density 0.009%

    No Known Activations