© 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. 113109
    Prev
    Next
    INDEX
    Explanations

    URLs and file paths

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

    line breaks or whitespace that separates sections of web content or document formatting.

    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
    hline
    -1.35
    -1.28
    >
    -1.24
    -1.24
     ليب
    -1.23
     criança
    -1.23
    mu
    -1.22
    its
    -1.21
    
    -1.20
    nloa
    -1.19
    POSITIVE LOGITS
     oyunu
    1.45
     recensement
    1.22
    之为
    1.19
     olabilir
    1.18
     serisi
    1.17
     lisesi
    1.12
    chtigkeit
    1.09
     ieder
    1.09
    mereka
    1.09
    ทุก
    1.09
    Activations Density 0.006%

    No Known Activations