© 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. 34-GEMMASCOPE-RES-131K
    7. 54128
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     already
    -0.88
    дцать
    -0.86
    Carriera
    -0.82
    osoever
    -0.78
    ემ
    -0.78
     뒤
    -0.78
     sources
    -0.74
    हाँ
    -0.73
     shape
    -0.73
     sixty
    -0.73
    POSITIVE LOGITS
    移動
    0.92
     one
    0.88
    Dettagli
    0.83
    빡
    0.82
     yılı
    0.82
     animato
    0.82
     mouseClicked
    0.78
    Mitte
    0.77
    0.75
    诧
    0.75
    Activations Density 0.003%

    No Known Activations