© 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. 90955
    Prev
    Next
    INDEX
    Explanations

    API and implementation

    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
     different
    -0.84
     utilizes
    -0.82
    屢
    -0.78
     bereits
    -0.74
     held
    -0.74
     жидкости
    -0.73
    奎
    -0.73
     difficulties
    -0.72
     loses
    -0.72
     tenerife
    -0.72
    POSITIVE LOGITS
    API
    1.04
    ︡
    1.00
    api
    0.96
     intrigue
    0.91
     API
    0.91
    mbals
    0.90
     Вікі
    0.89
    IGNORE
    0.88
    orda
    0.88
     APIs
    0.86
    Activations Density 0.002%

    No Known Activations