© 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. 90462
    Prev
    Next
    INDEX
    Explanations

    deformation and displacement

    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
    especially
    -1.36
     herbes
    -1.35
    end
    -1.32
    including
    -1.27
     addirittura
    -1.27
    〽
    -1.25
    
    -1.24
    ICIONES
    -1.24
     persino
    -1.24
     veramente
    -1.23
    POSITIVE LOGITS
    ANIEL
    1.48
    我们的
    1.31
    ڧ
    1.30
    qué
    1.23
     اتحاد
    1.23
    dersfield
    1.19
    ManagedBean
    1.19
     beginnt
    1.17
     complacent
    1.16
    rías
    1.16
    Activations Density 0.068%

    No Known Activations