© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10176
    Prev
    Next
    INDEX
    Explanations

    `[type`, `[improved`, `[written`, `[http`, `[1]`, `[2.03,`, `[ -8,`, `[^2]]{}`

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

    opening square brackets in code or structured data formats.

    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
    d
    -2.69
    k
    -2.47
     believes
    -2.47
     indicates
    -2.45
     gets
    -2.42
    a
    -2.41
     provides
    -2.31
     ensures
    -2.30
     '
    -2.23
    The
    -2.22
    POSITIVE LOGITS
    鲩
    2.69
    ਃ
    2.67
    
    2.41
    玙
    2.39
    釤
    2.31
    这件事情
    2.31
    薅
    2.30
    锇
    2.28
    屃
    2.28
    偻
    2.28
    Activations Density 0.029%

    No Known Activations