© 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. 48513
    Prev
    Next
    INDEX
    Explanations

    underworld and nether regions

    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
    一旁的
    -2.36
    訁
    -2.31
    饪
    -2.30
    li
    -2.16
    2
    -2.11
    一旁
    -2.11
    -2.09
    賸
    -2.09
    In
    -2.06
    羮
    -2.06
    POSITIVE LOGITS
     of
    2.31
     why
    2.03
    艫
    1.95
    薦
    1.94
     igreja
    1.93
     biela
    1.91
    天空
    1.91
    ニーカー
    1.90
    恫
    1.88
     вода
    1.88
    Activations Density 0.008%

    No Known Activations