© 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. 90725
    Prev
    Next
    INDEX
    Explanations

    RestController and Restorative words

    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
    ࿊
    -3.17
    iſter
    -3.09
    鼕
    -3.06
    寕
    -2.95
    伈
    -2.95
    䊐
    -2.92
    鮰
    -2.86
    ߭
    -2.84
     kedi
    -2.84
    鏷
    -2.80
    POSITIVE LOGITS
     To
    2.94
     Roughly
    2.91
     Undoubtedly
    2.89
    想必
    2.80
     Because
    2.67
    といって
    2.61
     Given
    2.59
     Many
    2.59
    on
    2.58
    In
    2.55
    Activations Density 0.007%

    No Known Activations