© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13918
    Prev
    Next
    INDEX
    Explanations

    common grammatical structures

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

    The neuron fires strongly on content-bearing words—important nouns, verbs, and adjectives—rather than on light 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_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
     niečo
    -1.27
     different
    -1.13
     wouldn
    -1.12
     intenção
    -1.11
     doesn
    -1.09
     wanted
    -1.09
     Wouldn
    -1.09
     получилось
    -1.09
    に行って
    -1.09
     then
    -1.07
    POSITIVE LOGITS
    ｢
    1.16
     gré
    1.08
    edade
    1.06
    llllllll
    1.06
    lllllll
    1.05
    lllll
    1.05
    漢字
    1.05
    長男
    1.05
    علي
    1.02
    ͔
    0.99
    Activations Density 0.026%

    No Known Activations