© 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. 10324
    Prev
    Next
    INDEX
    Explanations

    what follows "after"

    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
     ANOTHER
    -2.20
    m
    -2.09
    c
    -1.94
     enregistrer
    -1.90
    也非常
    -1.88
    場合があります
    -1.86
    mathrm
    -1.86
    とともに
    -1.80
     cliquer
    -1.80
     are
    -1.78
    POSITIVE LOGITS
     since
    1.73
     this
    1.65
    </em>
    1.64
     beira
    1.60
     技術
    1.59
    ichtete
    1.59
    ");
    1.57
    嫌い
    1.52
     來
    1.52
    </h2>
    1.51
    Activations Density 0.004%

    No Known Activations