© 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. 71344
    Prev
    Next
    INDEX
    Explanations

    titles and headings

    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
    meuble
    -1.80
     generell
    -1.64
    utentic
    -1.59
    minin
    -1.55
    artiges
    -1.50
    hk
    -1.48
    montre
    -1.47
     denne
    -1.47
    mètres
    -1.46
    ellites
    -1.45
    POSITIVE LOGITS
     äußer
    1.85
     a
    1.83
    ’)
    1.58
    小结
    1.52
     patria
    1.50
    みます
    1.47
    图源
    1.45
     überras
    1.41
    点此
    1.39
     Bestandteil
    1.39
    Activations Density 0.015%

    No Known Activations