© 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. 42222
    Prev
    Next
    INDEX
    Explanations

    post navigation and compound words

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    沨
    -2.83
    ’
    -2.66
     fazendo
    -2.58
     tentando
    -2.50
    WHAT
    -2.50
    har
    -2.48
    看似
    -2.36
    氿
    -2.36
     altamente
    -2.34
     procurando
    -2.34
    POSITIVE LOGITS
    鐃
    2.94
    門口
    2.84
    妺
    2.77
    鏐
    2.75
     perplexing
    2.73
    噚
    2.70
    ">*
    2.63
    壟
    2.58
    沬
    2.55
    嬋
    2.52
    Activations Density 0.056%

    No Known Activations