© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 11910
    Prev
    Next
    INDEX
    Explanations

    countries and cities in Cyrillic

    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
     diesem
    -1.53
    夘
    -1.52
     tua
    -1.38
    嚒
    -1.37
    푎
    -1.37
     ragazzo
    -1.34
    幃
    -1.33
     secolo
    -1.32
    ࿚
    -1.31
    踅
    -1.31
    POSITIVE LOGITS
    してしまった
    1.44
    ,
    1.27
     всіх
    1.20
     Création
    1.19
     (
    1.19
     recognisable
    1.17
    ウィキ
    1.16
     Histórico
    1.16
    が欲しい
    1.15
    了两
    1.13
    Activations Density 0.129%

    No Known Activations