© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 38689
    Prev
    Next
    INDEX
    Explanations

    full followed by descriptor

    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
    Deferred
    -0.91
    oliber
    -0.90
     Deferred
    -0.86
    あまり
    -0.84
     apresenta
    -0.82
    rière
    -0.82
    ffered
    -0.81
     tecnologías
    -0.81
     interessante
    -0.80
    immediate
    -0.80
    POSITIVE LOGITS
     freedom
    0.99
    fledged
    0.98
     of
    0.92
     fled
    0.87
     components
    0.84
     accordance
    0.78
    aratus
    0.78
    Glossary
    0.77
     against
    0.75
     packed
    0.75
    Activations Density 0.016%

    No Known Activations