© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1695
    Prev
    Next
    INDEX
    Explanations

    palindrome

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is primarily detecting Portuguese words and phrases (indicating segments written in Portuguese).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     номер
    -0.76
     näky
    -0.69
    番号
    -0.68
    ochem
    -0.67
     DIRECTIONS
    -0.67
     Skyline
    -0.66
    绑
    -0.66
    tess
    -0.66
     switched
    -0.65
    wechsel
    -0.65
    POSITIVE LOGITS
     palindrome
    1.80
     pal
    1.61
     Pal
    1.55
    palindrome
    1.53
    Palindrome
    1.49
    Pal
    1.30
     madam
    1.23
    pal
    1.22
     symmetrical
    1.20
    팰
    1.15
    Activations Density 0.029%

    No Known Activations