© 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. 123926
    Prev
    Next
    INDEX
    Explanations

    programming union keywords

    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
     to
    -2.47
     don
    -2.30
     Германия
    -2.14
     isn
    -2.00
     Перейти
    -1.98
    鹋
    -1.97
    engertian
    -1.90
     одного
    -1.89
     jednej
    -1.88
     únicos
    -1.86
    POSITIVE LOGITS
    d
    2.38
     MUCH
    2.28
    寕
    2.27
     the
    2.20
    </sup>
    2.09
    "
    2.05
    嵓
    2.02
    The
    1.98
     kumaş
    1.96
    er
    1.94
    Activations Density 0.004%

    No Known Activations