© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7728
    Prev
    Next
    INDEX
    Explanations

    sentence beginnings

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

    This neuron lights up on very common English tokens (high-frequency “stop” words and other everyday 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_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
     with
    -1.92
     nepiecieš
    -1.60
     izvē
    -1.49
     Moderne
    -1.45
     iesp
    -1.39
     atento
    -1.36
     tikai
    -1.34
     パネル
    -1.34
    翻攝
    -1.34
     frites
    -1.32
    POSITIVE LOGITS
     I
    2.34
     gesamte
    1.77
    mayacak
    1.48
    甚至是
    1.43
     Bemerkungen
    1.42
     robić
    1.39
     revela
    1.38
    が無い
    1.38
     terminée
    1.38
     この
    1.35
    Activations Density 0.056%

    No Known Activations