© 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. 113279
    Prev
    Next
    INDEX
    Explanations

    acts in ways

    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
    趼
    -1.87
    tikai
    -1.77
    看了看
    -1.66
    ÑOS
    -1.64
     ilustracja
    -1.59
    んでいた
    -1.54
    乆
    -1.53
     neum
    -1.52
     hicieron
    -1.52
    ༀ
    -1.51
    POSITIVE LOGITS
     \\
    1.88
    </em>
    1.83
    或
    1.57
    ↵
    1.56
    "]
    1.54
     et
    1.52
    >");
    1.49
    }
    1.48
    ac
    1.46
    籥
    1.45
    Activations Density 0.037%

    No Known Activations