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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 42748
    Prev
    Next
    INDEX
    Explanations

    sports positions and actions

    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
     Vomiting
    -1.27
     Inflate
    -1.21
     oblasti
    -1.21
     rique
    -1.20
     áreas
    -1.17
     plethora
    -1.16
     każdego
    -1.13
     genuinely
    -1.13
     difficult
    -1.12
     devastating
    -1.12
    POSITIVE LOGITS
    seven
    1.33
    瞇
    1.33
    four
    1.30
    maining
    1.24
    gether
    1.19
     HALF
    1.19
     Fifteen
    1.19
     geração
    1.19
     Thirteen
    1.17
     Fourteen
    1.15
    Activations Density 0.036%

    No Known Activations