© 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. 70563
    Prev
    Next
    INDEX
    Explanations

    GPL license

    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
    ’
    -3.98
     Their
    -3.88
     It
    -3.33
     However
    -3.20
    -
    -3.11
    ized
    -2.88
     Historically
    -2.88
     Similarly
    -2.86
     Therefore
    -2.86
     Its
    -2.86
    POSITIVE LOGITS
    嵎
    3.22
    菝
    2.98
    鐧
    2.81
    脔
    2.81
     限定
    2.72
    銛
    2.72
    ItemBackground
    2.70
    猡
    2.69
    matory
    2.61
    ducers
    2.59
    Activations Density 0.099%

    No Known Activations