© 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. 87016
    Prev
    Next
    INDEX
    Explanations

    is prime or palindrome

    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
     LEAST
    -0.88
     diskusi
    -0.82
    　「
    -0.79
    तिक
    -0.79
    送料
    -0.79
    魷
    -0.78
     Duet
    -0.77
    Пусть
    -0.77
     Balloons
    -0.76
    Новые
    -0.76
    POSITIVE LOGITS
     equal
    1.05
     valid
    1.00
     palindrome
    0.99
     ana
    0.99
     gæ
    0.94
     prime
    0.93
     Ana
    0.93
     samma
    0.90
    羸
    0.88
     belong
    0.88
    Activations Density 0.054%

    No Known Activations