© 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. 10-GEMMASCOPE-RES-131K
    7. 60551
    Prev
    Next
    INDEX
    Explanations

    order and stability

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

    The neuron fires most strongly on mentions of “order,” especially in the phrase “law and order.”

    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
     to
    -2.53
     that
    -2.23
     wysokość
    -1.51
     jednej
    -1.41
    ным
    -1.40
     artísticas
    -1.35
     but
    -1.32
     Urteil
    -1.32
     adaptées
    -1.31
    うれ
    -1.30
    POSITIVE LOGITS
    อีก
    1.57
    fohlen
    1.54
    9
    1.51
    1
    1.35
    şam
    1.35
     beden
    1.35
    Thailand
    1.35
    Tämä
    1.34
    Venezuela
    1.34
     gömlek
    1.34
    Activations Density 0.014%

    No Known Activations