© 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. 76483
    Prev
    Next
    INDEX
    Explanations

    .DOCTYPE, .PDF, induced, Semiconductor

    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
     lavish
    -1.41
     supremely
    -1.32
     superbly
    -1.26
     epitom
    -1.24
     dazzling
    -1.23
     ingrained
    -1.23
     meticulously
    -1.22
     terribly
    -1.22
     furthering
    -1.21
     because
    -1.20
    POSITIVE LOGITS
    particularly
    1.54
     alguns
    1.45
     sentimentos
    1.44
     accentu
    1.35
    despite
    1.34
     geralmente
    1.31
    commonly
    1.31
     soooo
    1.30
     ofreci
    1.30
     algumas
    1.29
    Activations Density 0.008%

    No Known Activations