© 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. 42573
    Prev
    Next
    INDEX
    Explanations

    this + noun/adjective

    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
     with
    -2.39
     at
    -2.34
     for
    -2.14
     as
    -2.11
     after
    -1.84
     through
    -1.76
     your
    -1.72
     on
    -1.67
     without
    -1.64
     first
    -1.62
    POSITIVE LOGITS
     frança
    1.63
    AGAIN
    1.63
    didn
    1.61
     spearheaded
    1.57
    赑
    1.52
     bizarre
    1.46
    珰
    1.44
    ⇹
    1.43
    despite
    1.42
    であるが
    1.41
    Activations Density 0.088%

    No Known Activations