© 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. 91566
    Prev
    Next
    INDEX
    Explanations

    Polish suffixes (-ści, -ce, -ka)

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

    The neuron selectively responds to blocks of Polish text—especially words containing Polish diacritic characters.

    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
     of
    -1.17
     standardized
    -0.88
     recently
    -0.88
     fast
    -0.88
     powerful
    -0.87
    之心
    -0.84
     robust
    -0.84
     sophisticated
    -0.84
     massive
    -0.84
     huge
    -0.82
    POSITIVE LOGITS
     copiar
    1.02
     Sixers
    0.98
     stå
    0.94
     från
    0.91
     parlamentar
    0.90
    віду
    0.90
    ouvoir
    0.90
     cashback
    0.89
     оригіналу
    0.88
    astéroïdes
    0.88
    Activations Density 0.005%

    No Known Activations