© 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. 72866
    Prev
    Next
    INDEX
    Explanations

    the word simple

    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
    llavero
    -1.77
     火鍋
    -1.62
    richtig
    -1.61
    
    -1.53
    sowie
    -1.50
    踅
    -1.49
    ⻓
    -1.49
     trenes
    -1.48
    DÉ
    -1.48
    fassen
    -1.47
    POSITIVE LOGITS
     if
    1.84
    or
    1.63
    :
    1.58
    er
    1.49
    c
    1.48
    .
    1.44
    to
    1.44
    id
    1.41
    A
    1.41
    at
    1.40
    Activations Density 0.033%

    No Known Activations