© 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. 22-GEMMASCOPE-RES-131K
    4. 39737
    Prev
    Next
    INDEX
    Explanations

    game scores and outcomes

    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
    ioterapia
    -0.90
    MAR
    -0.86
    𝒌
    -0.84
    logically
    -0.83
    вут
    -0.82
    摂取
    -0.82
    emia
    -0.81
     vgl
    -0.80
     triunfo
    -0.80
    nické
    -0.79
    POSITIVE LOGITS
     their
    0.94
     arasındaki
    0.86
    Smit
    0.84
     recette
    0.80
    Ещё
    0.79
    Экономи
    0.78
     enhancing
    0.77
    utkan
    0.77
    Kah
    0.76
    انى
    0.76
    Activations Density 0.038%

    No Known Activations