© 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. 22-GEMMASCOPE-RES-131K
    7. 236
    Prev
    Next
    INDEX
    Explanations

    particle size

    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
    utilizzo
    -1.22
     правительства
    -1.13
     camicia
    -1.11
     обслуживание
    -1.08
    などは
    -1.07
    وفق
    -1.06
    Martina
    -1.05
     gostar
    -1.05
     consideró
    -1.05
    のための
    -1.02
    POSITIVE LOGITS
     size
    1.74
     sizes
    1.45
     méret
    1.32
     сахара
    1.29
     botanique
    1.27
    子さん
    1.25
    Size
    1.22
    liputi
    1.20
     larger
    1.20
    size
    1.20
    Activations Density 0.113%

    No Known Activations