© 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. 10-GEMMASCOPE-RES-131K
    7. 105566
    Prev
    Next
    INDEX
    Explanations

    introducing descriptive clauses

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

    The neuron strongly lights up on verbs—especially participial (“–ing”) forms and other main verb forms—throughout running text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     l
    -1.62
     K
    -1.57
     h
    -1.49
     there
    -1.45
     L
    -1.45
     }
    -1.39
     k
    -1.38
     *
    -1.38
     s
    -1.34
     (
    -1.34
    POSITIVE LOGITS
     télécharger
    1.65
     贝
    1.48
     rése
    1.41
     célè
    1.41
     Reſ
    1.40
    adah
    1.38
    鹀
    1.38
     炒
    1.38
     verhind
    1.35
     动漫
    1.34
    Activations Density 0.146%

    No Known Activations