© 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. 75073
    Prev
    Next
    INDEX
    Explanations

    code declarations

    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
    1
    -1.79
    兩人
    -1.70
    3
    -1.57
    6
    -1.51
    相変わらず
    -1.48
    [
    -1.46
     offizi
    -1.43
     $
    -1.36
     двох
    -1.35
     варианты
    -1.34
    POSITIVE LOGITS
    🧐
    1.62
     pleaf
    1.59
     batas
    1.56
    hasMany
    1.55
     filma
    1.51
     setiap
    1.50
     batata
    1.49
    😨
    1.49
    🤫
    1.48
     principi
    1.48
    Activations Density 0.004%

    No Known Activations