© 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. 13331
    Prev
    Next
    INDEX
    Explanations

    states followed by participles

    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
    Fungsi
    -1.07
     décé
    -1.05
    IVATE
    -1.05
     gallbladder
    -1.04
     ())
    -1.02
     to
    -1.02
    ᾳ
    -1.02
    ✏
    -1.02
    ských
    -0.99
     therein
    -0.98
    POSITIVE LOGITS
     further
    1.62
     by
    1.32
     followed
    1.06
     supplemented
    1.04
    のですが
    1.03
     następnie
    1.01
     supported
    1.00
     توسط
    0.98
     extended
    0.96
     głównie
    0.96
    Activations Density 0.128%

    No Known Activations