© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 21380
    Prev
    Next
    INDEX
    Explanations

    low quantities or conditions

    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_10/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
    くちゃ
    -1.42
     Theore
    -1.27
    颳
    -1.27
     بھی
    -1.26
     Neuros
    -1.21
    🍔
    -1.20
     ‘‘
    -1.20
    TED
    -1.17
     to
    -1.17
     fatale
    -1.16
    POSITIVE LOGITS
    午後
    1.24
     gelukkig
    1.21
     geschikt
    1.20
     decirle
    1.20
    </sup>
    1.20
    是什么意思
    1.18
    ที่มี
    1.17
     advise
    1.16
    URRED
    1.16
     perdón
    1.16
    Activations Density 0.146%

    No Known Activations