© 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. 112387
    Prev
    Next
    INDEX
    Explanations

    works well

    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
    ೢ
    -2.27
    
    -2.23
    聍
    -2.22
     a
    -2.19
    僦
    -2.16
    摇了
    -2.14
     superstar
    -2.13
    が欲しい
    -2.11
    を読
    -2.06
    䊐
    -2.06
    POSITIVE LOGITS
    8
    2.59
    4
    2.47
    5
    2.20
    2
    2.09
    7
    1.98
    3
    1.94
    就是
    1.91
    也很
    1.90
    一
    1.88
    6
    1.84
    Activations Density 0.017%

    No Known Activations