© 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. 90288
    Prev
    Next
    INDEX
    Explanations

    keynote speeches and addresses

    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
    </h3>
    -3.16
     you
    -2.86
     are
    -2.80
    </th>
    -2.39
    ,"
    -2.31
    "
    -2.27
    </i>
    -2.25
    ⸨
    -2.22
    就算是
    -2.14
    },
    -2.13
    POSITIVE LOGITS
     أيض
    2.50
     火锅
    2.44
    ‪.‬‬
    2.36
    sandalia
    2.34
    鸶
    2.28
    ܖ
    2.25
    螄
    2.14
    緲
    2.13
    Ꮔ
    2.13
     土産
    2.11
    Activations Density 0.002%

    No Known Activations