© 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. 1583
    Prev
    Next
    INDEX
    Explanations

    Japanese and Chinese characters

    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
    ֶּ
    -0.78
     betrek
    -0.77
     toegang
    -0.77
    /*---
    -0.75
    newest
    -0.75
    shout
    -0.73
    べる
    -0.73
    flowering
    -0.72
     dagelijks
    -0.72
    prueba
    -0.71
    POSITIVE LOGITS
    dific
    0.93
    ఇ
    0.90
    NET
    0.88
    bogen
    0.84
     стола
    0.83
    \]
    0.81
    getKeyCode
    0.81
     おしゃれ
    0.81
     stickers
    0.79
     svého
    0.79
    Activations Density 0.013%

    No Known Activations