© 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. 102167
    Prev
    Next
    INDEX
    Explanations

    ua-

    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
    鎗
    -2.69
    咵
    -2.64
     illustratie
    -2.63
     ()
    -2.59
     anbef
    -2.58
    蕯
    -2.56
     テラス
    -2.55
    ൎ
    -2.53
    籟
    -2.53
    しないで
    -2.53
    POSITIVE LOGITS
     
    2.86
    ua
    2.73
    {
    2.61
    もちろん
    2.58
     помогают
    2.41
    “
    2.36
    ia
    2.31
    on
    2.28
     quintessential
    2.22
    '
    2.20
    Activations Density 0.011%

    No Known Activations