© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 101722
    Prev
    Next
    INDEX
    Explanations

    subjects undertaking actions

    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
     by
    -2.06
     after
    -2.05
    );
    -1.72
     would
    -1.69
     good
    -1.63
     will
    -1.62
     also
    -1.61
     resulting
    -1.58
     notable
    -1.55
     could
    -1.49
    POSITIVE LOGITS
    我们
    1.73
    甍
    1.65
     mauva
    1.59
    我們
    1.57
    เรา
    1.57
     سایر
    1.56
    炱
    1.54
     ainfi
    1.53
    ícias
    1.52
    nimmt
    1.52
    Activations Density 0.025%

    No Known Activations