© 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. 158
    Prev
    Next
    INDEX
    Explanations

    responsible for overseeing or managing

    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
     verdaderas
    -1.52
     dañ
    -1.48
     obligado
    -1.43
     they
    -1.42
     lecciones
    -1.36
    alami
    -1.32
     themselves
    -1.32
     ejerc
    -1.29
     gründ
    -1.27
     éstos
    -1.23
    POSITIVE LOGITS
     of
    1.93
     and
    1.78
    🤡
    1.48
    💔
    1.41
    😱
    1.41
     inox
    1.40
    😶
    1.40
    ooooo
    1.40
     appartement
    1.37
    😑
    1.35
    Activations Density 0.067%

    No Known Activations