© 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. 110935
    Prev
    Next
    INDEX
    Explanations

    processed verbs

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

    This neuron mainly fires on words ending in “ed” (i.e. past-tense or past-participle forms).

    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
    e
    -2.98
     några
    -2.75
    踱
    -2.52
    ⮜
    -2.48
    {
    -2.39
     pomen
    -2.38
    k
    -2.38
    AutoModerator
    -2.38
    騷
    -2.38
     остальные
    -2.36
    POSITIVE LOGITS
    '
    4.22
    s
    2.97
    "
    2.75
    ness
    2.75
    食感
    2.73
    atser
    2.67
     They
    2.64
    .
    2.45
    翾
    2.44
    玙
    2.44
    Activations Density 2.040%

    No Known Activations