© 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. 22-GEMMASCOPE-RES-131K
    7. 34543
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives and emotions

    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_22/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
     EconPapers
    -1.36
    rendre
    -1.19
    誰か
    -1.18
    ЛЮ
    -1.16
    ほら
    -1.16
     or
    -1.16
    FONTE
    -1.15
     грамм
    -1.14
    ВОД
    -1.13
    Prijs
    -1.12
    POSITIVE LOGITS
     serta
    1.01
    mathrm
    1.00
    前は
    0.99
    tský
    0.98
     {}
    0.98
     whoever
    0.96
     kepada
    0.95
    tuce
    0.94
    是非常
    0.94
    そして
    0.92
    Activations Density 0.009%

    No Known Activations