© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57126
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    DISABLED
    -0.84
     ը
    -0.82
    fund
    -0.80
     insisting
    -0.80
    ujudkan
    -0.79
     values
    -0.79
     insum
    -0.77
     flowing
    -0.76
    Values
    -0.76
     luoghi
    -0.75
    POSITIVE LOGITS
    Andrei
    0.76
     nästan
    0.76
    Grpc
    0.76
    addProperty
    0.75
    性
    0.74
    mongodb
    0.74
    garh
    0.73
    しの
    0.73
     especí
    0.70
    Andrey
    0.70
    Activations Density 0.042%

    No Known Activations