© 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. 8389
    Prev
    Next
    INDEX
    Explanations

    specific points in time

    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
    </em>
    -1.78
     pretože
    -1.73
    l
    -1.64
     keď
    -1.63
    </strong>
    -1.58
     gdyż
    -1.54
    因为它
    -1.49
     to
    -1.49
    </h3>
    -1.47
    </u>
    -1.45
    POSITIVE LOGITS
     dipasang
    1.80
     lancar
    1.70
     déput
    1.69
     familières
    1.59
     memasang
    1.57
     Kulit
    1.55
    〜〜
    1.55
     Songtext
    1.54
    〜！
    1.54
     two
    1.53
    Activations Density 0.088%

    No Known Activations