© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99033
    Prev
    Next
    INDEX
    Explanations

    high current, normally come, dose-dependently

    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
     five
    -0.90
     Five
    -0.75
    するのが
    -0.70
     ostensibly
    -0.68
     veli
    -0.66
    Triggered
    -0.63
     furi
    -0.63
     obviously
    -0.63
     phenomenal
    -0.62
     напря
    -0.61
    POSITIVE LOGITS
    #.
    0.75
    Pří
    0.75
    enment
    0.71
    textSize
    0.71
    embley
    0.70
    mapbox
    0.70
     redaktion
    0.70
    ()?;
    0.70
    itsa
    0.70
    {#
    0.70
    Activations Density 0.098%

    No Known Activations