© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1200
    Prev
    Next
    INDEX
    Explanations

    analytical standards and spikes

    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
     about
    -1.84
    ERS
    -1.34
    zości
    -1.32
     modificaciones
    -1.30
     categorías
    -1.24
     colecciones
    -1.23
     proyectos
    -1.23
    悻
    -1.23
     otorga
    -1.23
    neous
    -1.20
    POSITIVE LOGITS
    Etape
    1.17
    Topping
    1.12
    getNombre
    1.10
     Since
    1.09
    Sinopse
    1.05
     när
    1.05
    CONCLUSION
    1.05
     decreto
    1.04
     した
    1.03
    ACKNOWLEDG
    1.03
    Activations Density 0.073%

    No Known Activations