© 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. 58449
    Prev
    Next
    INDEX
    Explanations

    new features and innovations

    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
     actuelle
    -1.48
    桫
    -1.42
    ｶ
    -1.40
     peculiarities
    -1.38
    használ
    -1.38
    你现在
    -1.35
    particularly
    -1.34
     особенно
    -1.30
    чев
    -1.29
    的过程
    -1.28
    POSITIVE LOGITS
    .’
    1.38
     ‘
    1.37
    梘
    1.36
    𝟔
    1.33
     manten
    1.31
     similar
    1.30
    ဴ
    1.30
     wilayah
    1.30
    × 
    1.27
    UnifiedTopology
    1.24
    Activations Density 0.060%

    No Known Activations