© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 86085
    Prev
    Next
    INDEX
    Explanations

    numbers and ratings

    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
    \
    -3.59
    .
    -2.64
      
    -2.17
    ]
    -2.17
    <i>
    -2.06
     continúas
    -2.00
     separate
    -2.00
     were
    -1.96
     augmented
    -1.94
    ┴
    -1.91
    POSITIVE LOGITS
    ‪.‬‬
    2.48
    ustomed
    2.16
     вони
    2.13
    ⣞
    2.09
     inspiré
    2.09
     半袖
    2.05
     ทำ
    2.05
    ettbewerb
    2.03
    訁
    1.99
     היא
    1.98
    Activations Density 0.009%

    No Known Activations