© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40243
    Prev
    Next
    INDEX
    Explanations

    technical terms and specific names

    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
    </td>
    -2.33
    感じ
    -2.22
    𓆜
    -2.13
    os
    -2.08
    ྜ
    -2.06
     Their
    -2.03
    л
    -2.00
    da
    -2.00
    इटम
    -1.99
    儈
    -1.98
    POSITIVE LOGITS
     ответил
    1.96
     його
    1.96
    antiago
    1.93
     classifying
    1.92
    もしくは
    1.84
     使っ
    1.83
    擼
    1.82
    </strong>
    1.80
    ں
    1.79
     schien
    1.78
    Activations Density 0.015%

    No Known Activations