© 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. 66152
    Prev
    Next
    INDEX
    Explanations

    past actions and their consequences

    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
     your
    -1.73
     can
    -1.45
     people
    -1.34
     protože
    -1.30
    ائه
    -1.25
     you
    -1.24
     in
    -1.24
     jūs
    -1.22
     congrat
    -1.21
    mathrm
    -1.20
    POSITIVE LOGITS
     gastronomía
    1.41
    Again
    1.41
    Their
    1.38
    them
    1.36
     tecnológicos
    1.35
    nitř
    1.34
     partito
    1.31
     Soit
    1.31
     bolsos
    1.30
    maintained
    1.30
    Activations Density 0.065%

    No Known Activations