© 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. 10-GEMMASCOPE-RES-131K
    4. 105438
    Prev
    Next
    INDEX
    Explanations

    HTML structure or code components

    np_acts-logits-general · gemini-2.5-flash-lite

    class names in HTML and code, particularly when they appear in element attributes like `class="searchForm"` or `class="Container"`.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     such
    -1.41
    landais
    -1.31
    aktivi
    -1.30
    атр
    -1.30
     foran
    -1.20
     }))
    -1.19
     pág
    -1.18
     snabb
    -1.17
    </th>
    -1.16
     ahí
    -1.16
    POSITIVE LOGITS
     всі
    1.48
    chene
    1.44
     only
    1.38
     說
    1.35
     этого
    1.35
     všech
    1.35
     все
    1.28
    その
    1.27
     aceptar
    1.27
     его
    1.24
    Activations Density 0.119%

    No Known Activations