© 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. 11843
    Prev
    Next
    INDEX
    Explanations

    morbid, colorectal, Minneapolis

    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
    *
    -3.31
    ↵↵
    -3.13
     Each
    -3.09
     vollständ
    -3.06
     We
    -3.02
     
    -2.91
    する
    -2.77
     After
    -2.72
    {
    -2.70
     großer
    -2.69
    POSITIVE LOGITS
    遢
    3.16
    閦
    3.11
    ꜆
    3.11
    埽
    3.09
    ⌵
    3.09
    鯪
    2.98
     kapas
    2.97
    幛
    2.89
    ╽
    2.89
    y
    2.89
    Activations Density 0.007%

    No Known Activations