© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 25882
    Prev
    Next
    INDEX
    Explanations

    counting days or length

    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
     while
    -1.18
    为了
    -0.99
     详情
    -0.98
    仪式
    -0.98
    😌
    -0.98
     头像
    -0.97
    もあって
    -0.97
     任务
    -0.96
    🤣🤣
    -0.96
    壁纸
    -0.96
    POSITIVE LOGITS
     
    1.19
     Głów
    1.13
     Reſ
    1.06
    🥽
    1.03
     veranderen
    1.02
    ématiques
    1.02
    感は
    1.00
     parfois
    1.00
     Provides
    0.98
    libur
    0.98
    Activations Density 0.037%

    No Known Activations