© 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. 9082
    Prev
    Next
    INDEX
    Explanations

    assets under management

    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
    of
    -3.39
    籴
    -2.95
    銫
    -2.95
    ."
    -2.58
    ﹔
    -2.44
     abbiano
    -2.41
    身子
    -2.41
     erroneous
    -2.38
    缡
    -2.34
     allegro
    -2.30
    POSITIVE LOGITS
    汌
    2.88
    2.69
     mencionados
    2.61
     leur
    2.58
     También
    2.55
     могут
    2.53
     somber
    2.38
     tidak
    2.31
     Also
    2.31
     Además
    2.30
    Activations Density 0.007%

    No Known Activations