© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40519
    Prev
    Next
    INDEX
    Explanations

    making 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_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
     have
    -1.65
    ↵↵
    -1.48
    になって
    -1.38
    "});
    -1.35
    那些
    -1.27
     feo
    -1.27
    这种
    -1.27
     mangiare
    -1.25
    这个
    -1.23
    man
    -1.23
    POSITIVE LOGITS
    もちろん
    1.56
     akin
    1.45
    勿論
    1.42
    object
    1.41
     första
    1.39
     sozialen
    1.38
     this
    1.34
    了下
    1.34
    つづく
    1.34
    睒
    1.34
    Activations Density 0.019%

    No Known Activations