© 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. 74956
    Prev
    Next
    INDEX
    Explanations

    dividend, salivary gland

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

    financial terms related to dividends and company payouts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     ,"
    -2.61
     are
    -2.56
     \
    -2.53
    縢
    -2.50
     —
    -2.47
    
    -2.44
     ―
    -2.41
     waren
    -2.36
     Gefühle
    -2.34
    ↵
    -2.33
    POSITIVE LOGITS
    砗
    2.63
    珰
    2.55
     thema
    2.38
     花纹
    2.36
    岜
    2.34
    ↵↵
    2.27
     فاض
    2.23
     hans
    2.20
    来自于
    2.20
    isation
    2.16
    Activations Density 0.002%

    No Known Activations