© 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. 49219
    Prev
    Next
    INDEX
    Explanations

    Kawasaki, Live cell, sizeof, Cortical, Anata

    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
    日本酒
    -0.80
    athons
    -0.76
    ె
    -0.74
    openha
    -0.72
    ߰
    -0.71
     wouldnt
    -0.70
     Unbe
    -0.70
    PopMatrix
    -0.69
    Bari
    -0.69
    くん
    -0.69
    POSITIVE LOGITS
    annotation
    0.88
     fortune
    0.87
    Fortune
    0.85
    inject
    0.84
    say
    0.83
    érature
    0.82
     hello
    0.81
     MediaPlayer
    0.81
     Fortune
    0.80
    üse
    0.80
    Activations Density 0.010%

    No Known Activations