© 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. 39972
    Prev
    Next
    INDEX
    Explanations

    mise, met, coloque

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

    The neuron activates strongly on the French phrase “Mise à jour par” (and its components), i.e. French-language edit/update attributions.

    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
    𓋼
    -3.58
    m
    -2.98
    l
    -2.81
    w
    -2.77
    Y
    -2.75
    n
    -2.56
    x
    -2.53
     untuk
    -2.50
    𖡼
    -2.50
    ⃚
    -2.45
    POSITIVE LOGITS
     Provide
    2.44
     "
    2.31
    </strong>
    2.20
    就直接
    2.17
    の様子
    2.11
    埛
    2.11
     Eventually
    2.09
    饪
    2.09
    졍
    2.08
    ⟣
    2.00
    Activations Density 0.003%

    No Known Activations