© 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. 92346
    Prev
    Next
    INDEX
    Explanations

    math and probability questions

    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
    ">“
    -1.11
    ACCIÓN
    -1.02
    itig
    -0.94
    ？！”
    -0.94
    }{{
    -0.94
     تأثير
    -0.94
     belangrijk
    -0.92
     フィギュア
    -0.89
     påvir
    -0.88
    正好
    -0.88
    POSITIVE LOGITS
     $\
    1.45
     LaTeX
    1.42
    әһ
    1.22
     $
    1.14
     grasa
    1.14
     latex
    1.12
     solutions
    1.12
     students
    1.09
    student
    1.09
     Latex
    1.07
    Activations Density 0.492%

    No Known Activations