© 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. 73511
    Prev
    Next
    INDEX
    Explanations

    playing roles, games, or media

    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
    箆
    -1.43
     estaremos
    -1.36
     uživ
    -1.34
     campes
    -1.28
     podremos
    -1.24
     encontrarás
    -1.23
     zůst
    -1.23
     podrás
    -1.20
     dokonce
    -1.20
     mezi
    -1.19
    POSITIVE LOGITS
    played
    1.59
    play
    1.52
    ͛
    1.34
     played
    1.31
    很多
    1.28
    上海
    1.26
    一些
    1.25
    自己
    1.25
     cucchia
    1.22
     découver
    1.20
    Activations Density 0.070%

    No Known Activations