© 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. 124740
    Prev
    Next
    INDEX
    Explanations

    text that reads

    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
    ympto
    -1.37
    RACE
    -1.34
     péché
    -1.28
    geordneten
    -1.27
     trenes
    -1.24
     naturligt
    -1.23
    ynchronous
    -1.23
    ؤال
    -1.23
    ynchron
    -1.23
     frågan
    -1.21
    POSITIVE LOGITS
    </i>
    1.64
    ."
    1.55
    .”
    1.52
     terá
    1.49
    .“
    1.48
     provocó
    1.43
    ){
    1.39
    痦
    1.38
    罢了
    1.34
    ()));
    1.33
    Activations Density 0.025%

    No Known Activations