© 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. 34-GEMMASCOPE-RES-131K
    7. 11977
    Prev
    Next
    INDEX
    Explanations

    had + past participle

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

    The neuron selectively activates on content-bearing words—especially nouns (including proper names) and pronouns—rather than on common 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_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
    zką
    -0.96
     estão
    -0.96
    ようになる
    -0.94
    uller
    -0.92
     Abgerufen
    -0.92
    ţilor
    -0.89
     שהוא
    -0.86
     puedan
    -0.84
    と思いました
    -0.84
    就是
    -0.84
    POSITIVE LOGITS
     had
    7.19
     había
    4.63
     habían
    4.00
     hadn
    3.89
     είχε
    3.78
     havia
    3.77
     avait
    3.56
     aveva
    3.31
     avaient
    3.30
     hatte
    3.19
    Activations Density 0.281%

    No Known Activations