© 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. 8136
    Prev
    Next
    INDEX
    Explanations

    be related or correlated

    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
     recomiendo
    -1.32
     devuelve
    -1.19
     carrito
    -1.16
     БЕ
    -1.14
    сную
    -1.13
    MeasureSpec
    -1.13
    hishek
    -1.11
    顿时
    -1.10
    emplacement
    -1.09
     []:
    -1.08
    POSITIVE LOGITS
     ebenfalls
    1.13
    赛季
    1.08
     battled
    1.07
    也太
    1.04
     також
    1.03
     Confe
    1.02
    鄖
    1.02
     также
    1.02
     también
    1.02
     errone
    1.01
    Activations Density 0.355%

    No Known Activations