© 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. 104637
    Prev
    Next
    INDEX
    Explanations

    though or although

    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
    %;
    -2.00
    呖
    -1.98
    Тема
    -1.88
    瞜
    -1.88
     perna
    -1.88
    ’).
    -1.87
     薬局
    -1.84
    );
    -1.84
    <td>
    -1.84
     pascua
    -1.83
    POSITIVE LOGITS
    {
    2.47
    (
    2.23
    0
    1.95
    ',
    1.88
    1.81
    стойчи
    1.78
    *
    1.73
    помним
    1.73
    1
    1.73
    [
    1.72
    Activations Density 0.003%
    No Known Activations