© 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. 119737
    Prev
    Next
    INDEX
    Explanations

    presenting additional 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
    _
    -2.08
    </strong>
    -2.06
    What
    -1.87
    {
    -1.80
    9
    -1.78
     is
    -1.73
    </sup>
    -1.70
    2
    -1.66
     dejó
    -1.63
    How
    -1.63
    POSITIVE LOGITS
    鷽
    1.77
    んびり
    1.77
    鮡
    1.73
     camiset
    1.70
    >?
    1.66
     撮っ
    1.62
     mereka
    1.61
    ୫
    1.60
     fenomen
    1.57
     tary
    1.56
    Activations Density 0.009%

    No Known Activations