© 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. 123921
    Prev
    Next
    INDEX
    Explanations

    major/minor versioning, axes, ticks

    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
     in
    -1.97
     if
    -1.73
     [
    -1.73
    .”
    -1.65
     when
    -1.64
     because
    -1.62
     for
    -1.40
     there
    -1.39
    er
    -1.38
     or
    -1.38
    POSITIVE LOGITS
     geschlagen
    1.69
    2
    1.62
     lavable
    1.52
    鹟
    1.52
    鈊
    1.49
    Grafik
    1.48
    雖
    1.48
    same
    1.48
    Ꮉ
    1.48
    錸
    1.46
    Activations Density 0.017%

    No Known Activations