© 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. 4048
    Prev
    Next
    INDEX
    Explanations

    specific product launches

    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
     probably
    -1.05
     my
    -1.00
    森
    -0.93
     do
    -0.89
     only
    -0.87
     other
    -0.86
     good
    -0.83
     mainly
    -0.83
     say
    -0.82
     their
    -0.80
    POSITIVE LOGITS
     الأصل
    1.27
    jazd
    1.13
     originals
    1.05
     ['./
    0.94
     ['',
    0.91
     ejemplos
    0.90
     demandes
    0.90
     škole
    0.87
     BEAUTIFUL
    0.87
     alquiler
    0.87
    Activations Density 0.001%

    No Known Activations