© 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. 34-GEMMASCOPE-RES-131K
    7. 91886
    Prev
    Next
    INDEX
    Explanations

    survived by, musical dynasty, mutual consent, plaintiff-appellant

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

    The neuron fires on inflected verb forms—especially gerunds (“-ing”), past participles (“-ed”), and other non-base tense verb tokens.

    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
    }$.
    -0.86
     calientes
    -0.83
     verano
    -0.82
     menjel
    -0.81
     resurrected
    -0.81
     Penyakit
    -0.80
     Tài
    -0.80
     souhaitent
    -0.79
    unlike
    -0.78
     deseado
    -0.78
    POSITIVE LOGITS
     cherish
    1.20
     dominante
    1.00
     trist
    0.93
     his
    0.93
     perpétu
    0.90
    APPING
    0.89
    莴
    0.89
     vei
    0.88
     memories
    0.88
     memory
    0.88
    Activations Density 0.001%

    No Known Activations