© 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. 21894
    Prev
    Next
    INDEX
    Explanations

    atomic science and tech

    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
    "{\
    -2.25
    embley
    -2.25
    是啊
    -2.14
    是
    -2.14
     ambayo
    -2.14
    我們
    -2.13
    鉕
    -2.13
    We
    -2.13
    能在
    -2.13
     ikiwa
    -2.08
    POSITIVE LOGITS
    ’)
    2.89
     \
    2.44
    </strong>
    2.36
    </u>
    2.34
    倏
    2.30
    我一
    2.28
     Hinblick
    2.28
     reports
    2.27
    𖥧
    2.23
    目前的
    2.20
    Activations Density 0.004%

    No Known Activations