© 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. 86781
    Prev
    Next
    INDEX
    Explanations

    current state or time

    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
    <
    -2.78
    2
    -2.55
     في
    -2.47
     Ketika
    -2.45
     Ähn
    -2.41
    ":
    -2.39
    if
    -2.39
     Entsche
    -2.38
     Bestimm
    -2.36
     Meski
    -2.36
    POSITIVE LOGITS
    缐
    2.80
    鲣
    2.77
     noteworthy
    2.73
     seems
    2.70
    ेमाल
    2.69
     strives
    2.69
    摭
    2.69
     promotes
    2.66
    犇
    2.66
     superbly
    2.64
    Activations Density 0.048%

    No Known Activations