© 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. 34-GEMMASCOPE-RES-131K
    7. 110771
    Prev
    Next
    INDEX
    Explanations

    we conducted research

    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_34/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
     Работа
    -1.06
    čený
    -0.82
     Zelle
    -0.82
     kullanılan
    -0.78
    יצוני
    -0.78
     tejto
    -0.78
     volunte
    -0.77
     aufzu
    -0.77
     princí
    -0.77
     eingeladen
    -0.76
    POSITIVE LOGITS
     perform
    4.50
     performing
    4.38
     performed
    4.19
    进行
    4.06
     انجام
    4.00
     performs
    3.89
     conducting
    3.89
    Perform
    3.88
    Performing
    3.81
     conduct
    3.80
    Activations Density 0.289%

    No Known Activations