© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84363
    Prev
    Next
    INDEX
    Explanations

    software, systems, and brands

    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
    </em>
    -1.32
    ⅖
    -1.29
     تأ
    -1.23
    </h3>
    -1.23
    英寸
    -1.16
    ⅞
    -1.16
    ῖν
    -1.16
    ⁈
    -1.15
    </h2>
    -1.13
     एवं
    -1.13
    POSITIVE LOGITS
     πρ
    1.24
    Жит
    1.23
     близько
    1.23
    Життє
    1.22
     navire
    1.20
     accès
    1.16
    荭
    1.15
     СПб
    1.14
     mógł
    1.14
    สอง
    1.13
    Activations Density 0.161%

    No Known Activations