© 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. 66370
    Prev
    Next
    INDEX
    Explanations

    grammatical structures and keywords

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

    The neuron fires on words with common inflectional endings (e.g. –ed, –ing, –er) indicating tense, aspect, or degree.

    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
    ようです
    -1.16
     schreiben
    -1.10
    slika
    -1.08
    hyundai
    -1.02
    peugeot
    -1.00
    cuba
    -0.97
     istot
    -0.96
     duża
    -0.95
    jedno
    -0.95
     também
    -0.94
    POSITIVE LOGITS
    了许多
    1.18
    了不少
    1.13
     herido
    1.08
    tetten
    1.02
    ACKNOWLEDGEMENTS
    0.99
    Източници
    0.99
    <bos>
    0.98
     allegations
    0.96
    これは
    0.94
    最近は
    0.93
    Activations Density 0.000%

    No Known Activations