© 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. 34-GEMMASCOPE-RES-131K
    7. 3354
    Prev
    Next
    INDEX
    Explanations

    advance or progress

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

    The neuron is primarily triggered by occurrences of the stem “advanc” (i.e. the word “advance” and its morphological variants).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ｀
    -0.82
     Fink
    -0.82
     Weigh
    -0.77
     weigh
    -0.77
     Leonardo
    -0.76
     WEIGHT
    -0.73
    кация
    -0.72
    setWeight
    -0.72
    Weight
    -0.71
    lessness
    -0.70
    POSITIVE LOGITS
    progress
    0.88
     progress
    0.88
     Progress
    0.87
    ⵙ
    0.84
     ingresso
    0.82
     Advancement
    0.80
     진
    0.79
     advancement
    0.79
    谗
    0.78
    了不少
    0.78
    Activations Density 0.010%

    No Known Activations