© 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. 40110
    Prev
    Next
    INDEX
    Explanations

    data parsing

    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
     enjoy
    -0.90
    還能
    -0.90
    ladel
    -0.88
     eenen
    -0.87
     оконча
    -0.86
    чени
    -0.85
    ในการ
    -0.82
    efore
    -0.82
     erau
    -0.81
    zä
    -0.81
    POSITIVE LOGITS
    dieron
    0.93
    isatie
    0.90
    FileChooser
    0.88
    Sometimes
    0.87
    Serializable
    0.86
    ついに
    0.86
     pelúcia
    0.85
    höhung
    0.85
    taban
    0.85
    各有
    0.84
    Activations Density 0.005%

    No Known Activations