© 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. 794
    Prev
    Next
    INDEX
    Explanations

    scheduled events and performances

    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
    ddling
    -1.38
     également
    -1.34
     also
    -1.34
    (!__
    -1.27
    ásticos
    -1.27
     botões
    -1.23
     kompres
    -1.23
    }}{
    -1.21
    ÉE
    -1.20
    
    -1.20
    POSITIVE LOGITS
     Autó
    1.34
    mascara
    1.29
     with
    1.12
    lettre
    1.09
     reper
    1.09
    שלום
    1.08
    imgnum
    1.06
    berikut
    1.03
    異なる
    1.03
     рядом
    1.03
    Activations Density 0.042%

    No Known Activations