© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 130645
    Prev
    Next
    INDEX
    Explanations

    due to

    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
    "\"
    -1.61
    americanos
    -1.44
     ?',
    -1.36
    andReturn
    -1.36
    ViewChild
    -1.33
    lijah
    -1.31
    糖尿病
    -1.30
    ienė
    -1.30
    慙
    -1.28
    ærke
    -1.27
    POSITIVE LOGITS
     that
    2.44
     reasons
    1.77
     why
    1.59
    マジで
    1.50
     because
    1.49
    本当は
    1.45
     spôso
    1.45
    ドキドキ
    1.40
     Reasons
    1.39
    シャレ
    1.39
    Activations Density 0.080%

    No Known Activations