© 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. 65441
    Prev
    Next
    INDEX
    Explanations

    urls or links

    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
    -
    -1.45
    とはいえ
    -1.26
    though
    -1.26
    XXXXXX
    -1.20
     Spisak
    -1.20
     Irlanda
    -1.19
     Grecia
    -1.18
    ано
    -1.18
    :^{
    -1.17
     Geografia
    -1.17
    POSITIVE LOGITS
    producción
    1.42
     reuniones
    1.40
     pierwszej
    1.39
     maravillosas
    1.39
     regalías
    1.38
     invitaciones
    1.38
     najm
    1.36
    必须要
    1.34
     acoged
    1.32
     hígado
    1.32
    Activations Density 0.151%

    No Known Activations