© 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. 34-GEMMASCOPE-RES-131K
    4. 73722
    Prev
    Next
    INDEX
    Explanations

    names and biographical subjects

    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_34/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
    _
    -0.87
     souligné
    -0.81
     sambal
    -0.79
     beberapa
    -0.78
     hasilnya
    -0.76
     hadde
    -0.75
     yıllar
    -0.75
     Serikat
    -0.74
     asado
    -0.74
     untuk
    -0.73
    POSITIVE LOGITS
     новую
    0.96
    τερα
    0.91
    TextMessage
    0.91
    ckeys
    0.87
     Stag
    0.80
     Amic
    0.78
     deaf
    0.78
    ="'
    0.78
     respiración
    0.78
     candid
    0.77
    Activations Density 0.000%

    No Known Activations