© 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. 22-GEMMASCOPE-RES-131K
    7. 28230
    Prev
    Next
    INDEX
    Explanations

    diverse languages

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

    The neuron responds to punctuation symbols (especially apostrophes and similar punctuation tokens).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     all
    -1.28
     again
    -1.23
     another
    -1.20
     снова
    -1.14
    再び
    -1.13
    これも
    -1.12
     erneut
    -1.05
    などの
    -1.04
    ódnica
    -1.03
     cocky
    -1.03
    POSITIVE LOGITS
    がて
    1.11
    גות
    1.06
     entram
    1.02
     pè
    1.00
     plátano
    0.98
    same
    0.98
     beiden
    0.97
    ఝ
    0.95
     luy
    0.94
     exemples
    0.94
    Activations Density 0.055%

    No Known Activations