© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 29132
    Prev
    Next
    INDEX
    Explanations

    programming constructs

    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
     indispensables
    -1.69
     that
    -1.65
     of
    -1.61
     первом
    -1.48
    even
    -1.47
    硖
    -1.45
    erobic
    -1.45
    Bahkan
    -1.45
    Fö
    -1.45
    ном
    -1.43
    POSITIVE LOGITS
    ’
    1.99
    ↵↵
    1.91
    It
    1.88
     it
    1.78
    会有
    1.68
    它
    1.62
     tentando
    1.61
     ,‬
    1.58
    </sub>
    1.55
     männ
    1.55
    Activations Density 0.338%

    No Known Activations