© 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. 98486
    Prev
    Next
    INDEX
    Explanations

    order, type, block, appearance

    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
    <0xA3>
    -1.30
     pusi
    -1.07
    <bos>
    -1.06
    と思ったら
    -1.04
    ですが
    -1.03
     ویتامین
    -1.02
     conster
    -0.99
     angen
    -0.99
    theoretical
    -0.99
    轍
    -0.98
    POSITIVE LOGITS
    為に
    1.27
    producción
    0.94
    ülő
    0.91
    死ぬ
    0.91
     gemeenten
    0.91
    efeated
    0.88
    ohn
    0.88
     PROCEEDINGS
    0.88
     kleding
    0.88
    這
    0.87
    Activations Density 0.046%

    No Known Activations