© 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. 71576
    Prev
    Next
    INDEX
    Explanations

    color or code structure

    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
    軼
    -2.23
    你喜欢
    -2.08
    !!!!!
    -2.06
    ?”
    -2.06
    情況
    -2.06
    儀式
    -2.05
     unrelenting
    -2.05
     streamlined
    -2.02
    籐
    -2.00
    !”
    -1.98
    POSITIVE LOGITS
    OUTUBE
    2.67
    儅
    2.59
     estadounid
    2.45
     dieß
    2.38
     Dinas
    2.38
     peccato
    2.33
     trover
    2.31
    '
    2.28
     impianti
    2.25
     dezelve
    2.25
    Activations Density 0.000%

    No Known Activations