© 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. 105127
    Prev
    Next
    INDEX
    Explanations

    case conversion (uppercase, lowercase)

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

    words or tokens that are lowercase versions of proper nouns, technical terms, or keywords (especially when "lowercase" or case conversion is contextually relevant).

    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
    .
    -3.45
    er
    -3.27
    s
    -2.73
    '
    -2.56
     verkau
    -2.45
    {
    -2.38
    示意图
    -2.31
    “
    -2.31
    我会
    -2.25
     verheir
    -2.19
    POSITIVE LOGITS
    歘
    3.30
    }
    2.78
    霂
    2.63
    罍
    2.61
    𝄆
    2.53
    a
    2.50
    
    2.48
     ที่
    2.47
    并没有
    2.44
    浒
    2.42
    Activations Density 0.004%

    No Known Activations