© 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. 9502
    Prev
    Next
    INDEX
    Explanations

    cause change or progress

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

    The neuron is strongly triggered by occurrences of the lemma “drive” (in its various inflected forms such as drives, driving, driver).

    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
     يكن
    -1.08
    after
    -1.07
     Something
    -1.03
    这里是
    -1.03
    czych
    -1.00
     setelah
    -0.98
    لكن
    -0.96
    tières
    -0.93
    There
    -0.92
    cción
    -0.92
    POSITIVE LOGITS
     into
    1.89
     toward
    1.10
     ネイビー
    1.09
     hacia
    1.05
     drove
    1.02
     along
    1.00
     ベージュ
    1.00
     towards
    1.00
     adoption
    0.94
     down
    0.94
    Activations Density 0.028%

    No Known Activations