© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 64605
    Prev
    Next
    INDEX
    Explanations

    past tense states or actions

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

    The neuron strongly activates on words in actual narrative prose (continuous storytelling passages) and stays off for headings, metadata, or UI-like text.

    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
     we
    -1.73
    !
    -1.49
     праздни
    -1.45
    裆
    -1.44
     Năm
    -1.43
     җ
    -1.42
     &
    -1.41
     早餐
    -1.41
     souvent
    -1.41
     OGSÅ
    -1.41
    POSITIVE LOGITS
     was
    1.66
    鈑
    1.52
    靭
    1.50
     wasn
    1.48
    ५
    1.47
     their
    1.45
     his
    1.43
    濯
    1.43
    鏖
    1.42
     occafion
    1.41
    Activations Density 0.085%

    No Known Activations