© 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. 10-GEMMASCOPE-RES-131K
    7. 1316
    Prev
    Next
    INDEX
    Explanations

    .net and .org URLs

    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_10/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
    ୌ
    -1.78
    してしまう
    -1.76
     with
    -1.73
    晅
    -1.67
     about
    -1.67
    gucigalpa
    -1.67
    neutron
    -1.59
     only
    -1.59
    xiii
    -1.54
    してくれます
    -1.52
    POSITIVE LOGITS
    ütt
    1.59
     bym
    1.54
     предыду
    1.45
     („
    1.40
    3
    1.39
    1
    1.34
    ípio
    1.34
    所有
    1.30
    “
    1.28
    henswürdigkeiten
    1.27
    Activations Density 0.051%

    No Known Activations