© 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. 26910
    Prev
    Next
    INDEX
    Explanations

    mathematical models

    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
    кроссовки
    -1.35
     kado
    -1.34
     apparti
    -1.32
     TECHNIQUE
    -1.31
     cesar
    -1.31
     vixion
    -1.27
    擽
    -1.26
     TECH
    -1.25
     satria
    -1.23
     luxem
    -1.23
    POSITIVE LOGITS
     model
    1.98
     models
    1.59
     модели
    1.55
     with
    1.43
     modeled
    1.38
     system
    1.38
     simulation
    1.36
     simulations
    1.36
     economic
    1.34
     two
    1.33
    Activations Density 0.115%

    No Known Activations