© 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. 22-GEMMASCOPE-RES-131K
    7. 128594
    Prev
    Next
    INDEX
    Explanations

    return codes or results

    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_22/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
     furthermore
    -1.13
     refiere
    -0.97
     constitue
    -0.96
     ſome
    -0.90
     ofreció
    -0.89
     dirigió
    -0.88
    跸
    -0.88
    incorrect
    -0.87
    퐿
    -0.86
    更好地
    -0.85
    POSITIVE LOGITS
     if
    0.95
    Usually
    0.93
    According
    0.93
    ถ้า
    0.92
    If
    0.88
     blissful
    0.83
    ırı
    0.83
    Since
    0.82
    جوم
    0.81
    Despite
    0.81
    Activations Density 0.001%

    No Known Activations