© 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. 70731
    Prev
    Next
    INDEX
    Explanations

    sentences starting with 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
    ╿
    -3.27
    鏷
    -3.03
     แต่
    -2.78
    镦
    -2.63
    ⼥
    -2.59
    樒
    -2.56
    菝
    -2.44
    ಝ
    -2.42
    푣
    -2.42
    ’，
    -2.38
    POSITIVE LOGITS
    .
    3.05
    2
    2.50
     ,‬
    2.50
    祤
    2.45
    <em>
    2.42
    </h3>
    2.33
     feiert
    2.28
    www
    2.27
    {
    2.27
    5
    2.23
    Activations Density 0.018%

    No Known Activations