© 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. 70524
    Prev
    Next
    INDEX
    Explanations

    see you

    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
     betreffenden
    -1.85
     It
    -1.60
     for
    -1.55
     gewünschten
    -1.55
     erforderlichen
    -1.52
     
    -1.51
     verschill
    -1.45
     notwendigen
    -1.45
     Different
    -1.45
    要求
    -1.45
    POSITIVE LOGITS
    nimmt
    1.68
    tvguidetime
    1.66
     ${({
    1.55
    Ⓐ
    1.54
     mohou
    1.52
     všetkých
    1.49
    我们的
    1.47
    trauer
    1.46
     grafik
    1.45
     naše
    1.43
    Activations Density 0.010%

    No Known Activations