© 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. 105839
    Prev
    Next
    INDEX
    Explanations

    "one" followed by a single unit

    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
    -
    -2.11
    *
    -1.94
    who
    -1.81
    apparently
    -1.80
     некоторые
    -1.80
     durante
    -1.73
    {
    -1.73
    ers
    -1.70
    whose
    -1.69
    still
    -1.67
    POSITIVE LOGITS
    錞
    1.81
     Both
    1.74
    ächtige
    1.73
    Both
    1.70
     alin
    1.64
    ၞ
    1.64
     中式
    1.63
    /}
    1.60
     خبرگزاری
    1.59
    捭
    1.58
    Activations Density 0.014%

    No Known Activations