© 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. 3817
    Prev
    Next
    INDEX
    Explanations

    aria or Aria

    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
    \
    -3.08
     have
    -2.83
     from
    -2.75
     would
    -2.70
     is
    -2.56
     cannot
    -2.52
     atau
    -2.50
    ffeine
    -2.45
     for
    -2.44
    .’
    -2.41
    POSITIVE LOGITS
    皤
    2.77
    鹟
    2.59
    が少ない
    2.58
    Neces
    2.53
     andre
    2.52
    腼
    2.41
    DONT
    2.34
     externe
    2.34
    ⍽
    2.33
    {
    2.30
    Activations Density 0.000%

    No Known Activations