© 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. 118938
    Prev
    Next
    INDEX
    Explanations

    firearms and their use

    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
     définiti
    -1.73
    (
    -1.67
     fidé
    -1.53
     estimés
    -1.50
     excès
    -1.45
     vérit
    -1.42
     tinged
    -1.35
    櫚
    -1.34
     insistent
    -1.34
    )
    -1.34
    POSITIVE LOGITS
     and
    1.73
     used
    1.49
     have
    1.49
     request
    1.47
     requested
    1.45
     seek
    1.45
     watch
    1.40
    CADE
    1.40
     нужно
    1.38
     take
    1.37
    Activations Density 0.027%

    No Known Activations