© 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. 102277
    Prev
    Next
    INDEX
    Explanations

    try to do

    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
     by
    -2.19
     with
    -1.81
    when
    -1.58
     When
    -1.56
     來
    -1.53
    法规
    -1.53
     Numerous
    -1.52
    Most
    -1.52
    Typically
    -1.52
     on
    -1.49
    POSITIVE LOGITS
    心脏
    1.84
    iennes
    1.64
    seys
    1.59
     étaient
    1.56
    fizierung
    1.54
    vités
    1.53
    iture
    1.47
     legate
    1.45
     iprot
    1.44
    atecas
    1.42
    Activations Density 0.020%

    No Known Activations