© 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. 10-GEMMASCOPE-RES-131K
    7. 57623
    Prev
    Next
    INDEX
    Explanations

    vulgar language, fowl, transcendental numbers

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

    The neuron tends to light up on relatively uncommon, content‐bearing “keyword” tokens – i.e. distinctive or domain‐specific words rather than high‐frequency function words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     "
    -3.02
    D
    -2.88
     {
    -2.50
    ’,
    -2.39
     ‘
    -2.31
     tens
    -2.30
    を見
    -2.27
     одним
    -2.16
    SE
    -2.13
     возможностей
    -2.13
    POSITIVE LOGITS
    1
    2.58
    appliquer
    2.50
    with
    2.47
    蘼
    2.36
     умова
    2.31
    ſelves
    2.28
    ꦢ
    2.16
    繰り返
    2.14
    骉
    2.14
     prioriti
    2.13
    Activations Density 0.006%

    No Known Activations