© 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. 75864
    Prev
    Next
    INDEX
    Explanations

    you immediately step in

    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
    ultas
    -1.14
    ADORA
    -1.11
    ctools
    -1.02
    ynthesis
    -0.96
    usepackage
    -0.96
    erdings
    -0.95
    orkin
    -0.94
     vicina
    -0.91
     insegu
    -0.91
    entingan
    -0.91
    POSITIVE LOGITS
     immediately
    2.47
     greeted
    2.28
     сразу
    1.77
     Immediately
    1.77
    Immediately
    1.77
     instantly
    1.75
     immediate
    1.63
     greeting
    1.59
     greets
    1.56
     welcomed
    1.55
    Activations Density 0.022%

    No Known Activations