© 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. 68917
    Prev
    Next
    INDEX
    Explanations

    references to figures

    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
     in
    -2.13
    1
    -2.08
    2
    -1.98
     not
    -1.96
    4
    -1.95
    0
    -1.85
    9
    -1.80
    3
    -1.70
     is
    -1.70
    s
    -1.66
    POSITIVE LOGITS
     and
    2.28
    傒
    1.80
    っていたので
    1.73
    蓠
    1.68
     貓
    1.68
     juſ
    1.68
     ранее
    1.64
     Geraadpleegd
    1.62
     图案
    1.59
     ſever
    1.59
    Activations Density 0.031%

    No Known Activations