© 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. 111066
    Prev
    Next
    INDEX
    Explanations

    android manifest attributes

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

    technical Android development code and configuration content, particularly manifest files, stack traces, and API references.

    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
    
    -1.34
    AKI
    -1.34
     retratos
    -1.30
    '.'
    -1.27
     ló
    -1.27
    klub
    -1.26
    茭
    -1.26
    
    -1.25
     mtu
    -1.24
    ⚡
    -1.24
    POSITIVE LOGITS
    </h2>
    1.43
     férias
    1.29
    item
    1.27
     مشابه
    1.27
     記
    1.26
     подоб
    1.25
    Răsp
    1.23
    咙
    1.22
    It
    1.22
    なー
    1.20
    Activations Density 0.031%

    No Known Activations