© 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. 103262
    Prev
    Next
    INDEX
    Explanations

    category: followed by subject

    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
     texinfo
    -0.95
     kompon
    -0.95
     komfor
    -0.94
     produkter
    -0.93
    ържа
    -0.93
     kram
    -0.92
    DESCRIPCIÓN
    -0.91
     maravilla
    -0.91
     eier
    -0.90
     различни
    -0.90
    POSITIVE LOGITS
    </blockquote>
    1.01
    <eos>
    0.89
     lived
    0.82
     back
    0.81
    quirer
    0.81
    はコチラ
    0.79
     hometown
    0.77
     offiziell
    0.76
     and
    0.75
     try
    0.75
    Activations Density 0.032%

    No Known Activations