© 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. 1997
    Prev
    Next
    INDEX
    Explanations

    code components and actions

    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
     dekoratif
    -0.99
     میکنم
    -0.97
     meren
    -0.96
    ternos
    -0.94
    lovely
    -0.91
     metode
    -0.91
    massive
    -0.90
    Рис
    -0.90
     digitale
    -0.90
     CardView
    -0.89
    POSITIVE LOGITS
     also
    1.00
     tohto
    0.90
     regarding
    0.84
     envision
    0.83
    igraphy
    0.81
     zä
    0.81
    readFileSync
    0.80
     reform
    0.80
     cuando
    0.77
     revel
    0.76
    Activations Density 0.003%

    No Known Activations