© 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. 119930
    Prev
    Next
    INDEX
    Explanations

    i686 or i386 architectures

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

    references to i686 or i586 (32-bit x86 processor architectures).

    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
    ↵↵
    -2.98
     rús
    -2.28
    (
    -2.25
    ют
    -1.96
     resistentes
    -1.93
     modernas
    -1.91
     respectivas
    -1.87
     perplexed
    -1.83
     médecin
    -1.82
    茀
    -1.81
    POSITIVE LOGITS
    s
    2.89
    所以我
    2.47
    on
    2.30
    輊
    2.20
    缡
    2.17
    ates
    2.14
    那我
    2.03
     дать
    2.03
    but
    2.02
     valuta
    2.00
    Activations Density 0.008%

    No Known Activations