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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 105585
    Prev
    Next
    INDEX
    Explanations

    contribution limitations strengths novelty

    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
     about
    -1.98
    したもの
    -1.69
     dureza
    -1.49
    していると
    -1.47
     certainly
    -1.44
     specifically
    -1.43
    着她
    -1.43
    鸕
    -1.42
    するもの
    -1.42
    してた
    -1.42
    POSITIVE LOGITS
    </sup>
    1.69
    </em>
    1.52
    ſſen
    1.48
    힣
    1.43
     gris
    1.43
    有些
    1.41
    今年
    1.39
    去年
    1.39
    目前
    1.38
    </b>
    1.36
    Activations Density 0.133%

    No Known Activations