© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99112
    Prev
    Next
    INDEX
    Explanations

    wrestling

    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
     there
    -1.11
     圣诞
    -1.11
     विश्वसनीय
    -1.10
    zić
    -1.09
     库
    -1.05
     営業
    -1.05
     bibliothèque
    -1.03
     腳
    -1.03
     here
    -1.02
    кої
    -1.02
    POSITIVE LOGITS
    </strong>
    1.47
    ')";
    1.41
     "'";
    1.34
    nadequate
    1.27
    </b>
    1.24
     включая
    1.23
    republik
    1.18
    Agrade
    1.15
    `;
    1.13
    bzw
    1.13
    Activations Density 0.039%

    No Known Activations