© 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. 91298
    Prev
    Next
    INDEX
    Explanations

    recent studies

    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
     Nedir
    -1.12
     stakeholder
    -1.04
    ってきて
    -1.03
     Metabol
    -1.01
    🌻
    -0.98
    💓
    -0.96
    --
    -0.96
     prêtres
    -0.95
    🤍
    -0.95
     obtener
    -0.95
    POSITIVE LOGITS
     recent
    2.55
     recently
    2.16
     studies
    1.91
    Recent
    1.78
     evidence
    1.78
    Recently
    1.66
     Recent
    1.60
     it
    1.56
    recent
    1.54
     lately
    1.52
    Activations Density 0.411%

    No Known Activations