© 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. 807
    Prev
    Next
    INDEX
    Explanations

    actions on UI elements

    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
    ༷
    -1.77
     definitiv
    -1.73
     récla
    -1.67
     sellado
    -1.65
     Dinas
    -1.63
    氿
    -1.63
     ſ
    -1.63
     wann
    -1.61
     dó
    -1.60
    ofed
    -1.60
    POSITIVE LOGITS
     for
    3.14
     in
    2.42
     while
    2.31
     from
    2.30
     because
    2.27
     despite
    2.22
     without
    2.11
     including
    2.08
     during
    2.06
     throughout
    1.99
    Activations Density 0.012%

    No Known Activations