© 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. 57659
    Prev
    Next
    INDEX
    Explanations

    care for coins

    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
    <bos>
    -1.60
     in
    -1.56
     "
    -1.55
     different
    -1.52
    一波
    -1.49
    [:,
    -1.48
     more
    -1.46
     are
    -1.45
     It
    -1.42
    --;
    -1.38
    POSITIVE LOGITS
     venge
    1.80
     tarefas
    1.66
     automatiques
    1.63
     russes
    1.58
    iteľ
    1.56
     classiques
    1.55
    镲
    1.55
    個月
    1.54
     traditionnels
    1.52
     ordinaires
    1.52
    Activations Density 0.031%

    No Known Activations