© 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. 22-GEMMASCOPE-RES-131K
    4. 9613
    Prev
    Next
    INDEX
    Explanations

    closing parentheses in code

    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
    部隊
    -1.09
     ARISING
    -1.05
    捜査
    -1.05
     herido
    -1.05
    raire
    -1.04
    賄
    -1.04
    几人
    -1.01
    ANEOUS
    -1.00
    馳走
    -0.99
    了许多
    -0.98
    POSITIVE LOGITS
    感じで
    1.19
    を見つけ
    1.07
     Эти
    1.02
    感じが
    1.02
     contacter
    1.02
    を目指す
    0.99
    こともあり
    0.98
     обеспечивает
    0.98
    Оста
    0.97
    捽
    0.97
    Activations Density 0.009%

    No Known Activations