© 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. 34-GEMMASCOPE-RES-131K
    7. 1919
    Prev
    Next
    INDEX
    Explanations

    X of all

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

    The neuron fires on superlative or emphatic discourse markers that appear in “__ of all” or “above all”‐style phrases (e.g. “first of all,” “best of all,” “above all,” “most of all,” “last of all”).

    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
     zarówno
    -0.96
     wenigen
    -0.90
     solchen
    -0.89
     Begleitung
    -0.88
     erheb
    -0.88
    स्तु
    -0.88
     Schwierigkeiten
    -0.87
     verwendeten
    -0.86
     bekannten
    -0.86
     persön
    -0.85
    POSITIVE LOGITS
     all
    4.78
    all
    2.59
     всего
    2.25
     все
    1.88
    All
    1.84
     kaikk
    1.80
     همه
    1.80
     όλα
    1.60
     allt
    1.54
     anything
    1.52
    Activations Density 0.014%

    No Known Activations