© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84126
    Prev
    Next
    INDEX
    Explanations

    See minor, Q:, There are

    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
     '.';
    -1.54
    Even
    -1.51
     навіть
    -1.49
     blissful
    -1.47
     ingrained
    -1.46
     even
    -1.45
     eager
    -1.42
     oddly
    -1.38
     frantic
    -1.38
     unrelenting
    -1.38
    POSITIVE LOGITS
     militä
    1.60
    ⅝
    1.54
     broader
    1.48
     moviliz
    1.45
     ebenfalls
    1.43
    ⡂
    1.43
     lì
    1.41
     praticamente
    1.40
     fortemente
    1.38
     zowel
    1.38
    Activations Density 0.000%

    No Known Activations