© 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. 93942
    Prev
    Next
    INDEX
    Explanations

    palindromes containing "pal"

    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
    yelidikan
    -0.75
     Herbst
    -0.71
    '])
    -0.69
    рила
    -0.68
    红色
    -0.67
    udessa
    -0.64
     Symbols
    -0.64
    냥
    -0.64
     blew
    -0.64
    )</
    -0.63
    POSITIVE LOGITS
     pal
    3.41
     Pal
    2.63
     palindrome
    2.58
    pal
    2.53
    Pal
    2.41
     PAL
    2.06
    Palindrome
    1.99
    palindrome
    1.97
    PAL
    1.87
     Palmer
    1.59
    Activations Density 0.109%

    No Known Activations