© 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. 22-GEMMASCOPE-RES-131K
    7. 36091
    Prev
    Next
    INDEX
    Explanations

    topic starters and continuations

    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_22/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
     stück
    -1.09
     tästä
    -1.04
     schä
    -1.02
    čný
    -1.00
    長的
    -0.96
     Öffnen
    -0.96
    声
    -0.95
    Pairing
    -0.94
     rustling
    -0.93
     adaptado
    -0.93
    POSITIVE LOGITS
     precau
    1.18
    ՚
    1.17
     devia
    1.16
     ombro
    1.13
     будет
    1.13
     Câ
    1.11
    lihood
    1.10
    栒
    1.10
     biodivers
    1.09
     ihren
    1.07
    Activations Density 0.012%

    No Known Activations