© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73705
    Prev
    Next
    INDEX
    Explanations

    collaborative study, research, and partnerships

    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
     The
    -4.16
     decidedly
    -2.64
     Ensuring
    -2.50
     
    -2.42
     ''
    -2.41
     THERE
    -2.30
     当
    -2.30
     AMAZING
    -2.28
     เมื่อ
    -2.27
     MUCH
    -2.25
    POSITIVE LOGITS
    鋮
    2.89
    下一篇
    2.88
    ⢓
    2.80
    本章
    2.66
     intricate
    2.58
     emphasizes
    2.55
     intensely
    2.50
     setOpen
    2.50
     unrelenting
    2.48
    ኾ
    2.48
    Activations Density 0.003%

    No Known Activations